< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 85 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.8637. Min Act: -0.1700

Data Index: 6914449 (Open Web Text)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.7522. Min Act: -0.1700

Data Index: 1171235 (Open Web Text)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.7363. Min Act: -0.1700

Data Index: 6567045 (Open Web Text)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.7363. Min Act: -0.1700

Data Index: 2718034 (Open Web Text)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.7043. Min Act: -0.1700

Data Index: 8318082 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.7043. Min Act: -0.1700

Data Index: 6761718 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6883. Min Act: -0.1700

Data Index: 8496012 (Open Web Text)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6562. Min Act: -0.1700

Data Index: 7668231 (Open Web Text)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6402. Min Act: -0.1700

Data Index: 5753458 (Open Web Text)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6402. Min Act: -0.1700

Data Index: 5878294 (Open Web Text)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6080. Min Act: -0.1700

Data Index: 7151765 (Open Web Text)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6402. Min Act: -0.1700

Data Index: 4029028 (Open Web Text)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6241. Min Act: -0.1700

Data Index: 6382894 (Open Web Text)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6241. Min Act: -0.1700

Data Index: 1977550 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6080. Min Act: -0.1700

Data Index: 6809834 (Open Web Text)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6080. Min Act: -0.1700

Data Index: 235249 (Open Web Text)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6080. Min Act: -0.1700

Data Index: 5149320 (Open Web Text)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.5919. Min Act: -0.1700

Data Index: 434619 (Open Web Text)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.5919. Min Act: -0.1700

Data Index: 6027565 (Open Web Text)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.6080. Min Act: -0.1700

Data Index: 3828652 (Open Web Text)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #19