< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 41 in Layer 34

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.2965. Min Range: -10.2965

Max Act: 10.2965. Min Act: -0.1700

Data Index: 1811071 (Open Web Text)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.2965. Min Range: -10.2965

Max Act: 10.2965. Min Act: -0.1700

Data Index: 3179320 (Open Web Text)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.2965. Min Range: -10.2965

Max Act: 10.1090. Min Act: -0.1700

Data Index: 5411805 (Open Web Text)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.2965. Min Range: -10.2965

Max Act: 10.1715. Min Act: -0.1700

Data Index: 3043829 (Open Web Text)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.2965. Min Range: -10.2965

Max Act: 10.1715. Min Act: -0.1700

Data Index: 4916388 (Open Web Text)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.9215. Min Act: -0.1700

Data Index: 6243037 (Open Web Text)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.7965. Min Act: -0.1700

Data Index: 260430 (Open Web Text)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.7340. Min Act: -0.1700

Data Index: 6357659 (Open Web Text)

Max Activating Token Index: 622

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.7340. Min Act: -0.1700

Data Index: 6632152 (Open Web Text)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.7340. Min Act: -0.1700

Data Index: 3876640 (Open Web Text)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.6715. Min Act: -0.1700

Data Index: 1692124 (Open Web Text)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.6715. Min Act: -0.1700

Data Index: 8255202 (Open Web Text)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.6715. Min Act: -0.1700

Data Index: 8583439 (Open Web Text)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.6715. Min Act: -0.1700

Data Index: 4846298 (Open Web Text)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.6715. Min Act: -0.1700

Data Index: 1059414 (Open Web Text)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.5465. Min Act: -0.1700

Data Index: 3219546 (Open Web Text)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.5465. Min Act: -0.1700

Data Index: 396420 (Open Web Text)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.5465. Min Act: -0.1700

Data Index: 2468239 (Open Web Text)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.4840. Min Act: -0.1700

Data Index: 19632 (Open Web Text)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.2965. Min Range: -10.2965

Max Act: 9.4840. Min Act: -0.1700

Data Index: 1297245 (Open Web Text)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #19