< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 61 in Layer 47

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.9157. Min Act: -0.1700

Data Index: 5104688 (Open Web Text)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.8532. Min Act: -0.1700

Data Index: 5202860 (Open Web Text)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.7282. Min Act: -0.1700

Data Index: 1587296 (Open Web Text)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.6657. Min Act: -0.1700

Data Index: 3358541 (Open Web Text)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.6032. Min Act: -0.1700

Data Index: 1686303 (Open Web Text)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.6657. Min Act: -0.1700

Data Index: 5223392 (Open Web Text)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.5407. Min Act: -0.1700

Data Index: 7402994 (Open Web Text)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.5407. Min Act: -0.1700

Data Index: 1681706 (Open Web Text)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.4157. Min Act: -0.1700

Data Index: 2044884 (Open Web Text)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.4157. Min Act: -0.1700

Data Index: 3234483 (Open Web Text)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.4157. Min Act: -0.1700

Data Index: 2754616 (Open Web Text)

Max Activating Token Index: 894

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.4157. Min Act: -0.1700

Data Index: 6194415 (Open Web Text)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.3532. Min Act: -0.1700

Data Index: 6960594 (Open Web Text)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.3532. Min Act: -0.1700

Data Index: 21103 (Open Web Text)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.2907. Min Act: -0.1700

Data Index: 8114600 (Open Web Text)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.3532. Min Act: -0.1700

Data Index: 4877441 (Open Web Text)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.2907. Min Act: -0.1700

Data Index: 6612645 (Open Web Text)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.2907. Min Act: -0.1700

Data Index: 989669 (Open Web Text)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.1657. Min Act: -0.1700

Data Index: 4678749 (Open Web Text)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.9157. Min Range: -10.9157

Max Act: 10.2282. Min Act: -0.1700

Data Index: 3136329 (Open Web Text)

Max Activating Token Index: 511

Click toggle to see full text

Truncated

Full Text #19