< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6363 in Layer 45

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.5407. Min Act: -0.1700

Data Index: 2545540 (Open Web Text)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.4470. Min Act: -0.1700

Data Index: 7420802 (Open Web Text)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.3845. Min Act: -0.1700

Data Index: 3550386 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.3845. Min Act: -0.1700

Data Index: 2755675 (Open Web Text)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.3532. Min Act: -0.1700

Data Index: 3518681 (Open Web Text)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.2907. Min Act: -0.1700

Data Index: 2346115 (Open Web Text)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.2907. Min Act: -0.1700

Data Index: 635334 (Open Web Text)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.2595. Min Act: -0.1700

Data Index: 1133369 (Open Web Text)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.2595. Min Act: -0.1700

Data Index: 16494 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.2595. Min Act: -0.1700

Data Index: 8509631 (Open Web Text)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.2282. Min Act: -0.1700

Data Index: 8543054 (Open Web Text)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.2282. Min Act: -0.1700

Data Index: 4584695 (Open Web Text)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.1970. Min Act: -0.1700

Data Index: 5641118 (Open Web Text)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.1970. Min Act: -0.1700

Data Index: 635333 (Open Web Text)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.1970. Min Act: -0.1700

Data Index: 4656668 (Open Web Text)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.1970. Min Act: -0.1700

Data Index: 1458692 (Open Web Text)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.1657. Min Act: -0.1700

Data Index: 6503069 (Open Web Text)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.1657. Min Act: -0.1700

Data Index: 4900624 (Open Web Text)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.1657. Min Act: -0.1700

Data Index: 3517492 (Open Web Text)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.5407. Min Range: -7.5407

Max Act: 7.1032. Min Act: -0.1700

Data Index: 3033403 (Open Web Text)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #19