Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4784 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.4629. Min Act: -0.1700
Data Index: 375902 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.4004. Min Act: -0.1700
Data Index: 1656545 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.4316. Min Act: -0.1700
Data Index: 3653041 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.4004. Min Act: -0.1700
Data Index: 8409931 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.3691. Min Act: -0.1700
Data Index: 4387591 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.3379. Min Act: -0.1700
Data Index: 3987108 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.3379. Min Act: -0.1700
Data Index: 1778674 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.2754. Min Act: -0.1700
Data Index: 6040769 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.2754. Min Act: -0.1700
Data Index: 577238 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.2754. Min Act: -0.1700
Data Index: 1327307 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.2129. Min Act: -0.1700
Data Index: 2175051 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.2129. Min Act: -0.1700
Data Index: 6135868 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.1816. Min Act: -0.1700
Data Index: 8477619 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.1816. Min Act: -0.1700
Data Index: 849359 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.1504. Min Act: -0.1700
Data Index: 3458066 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.1816. Min Act: -0.1700
Data Index: 4291793 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.1191. Min Act: -0.1700
Data Index: 3575937 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.1191. Min Act: -0.1700
Data Index: 8698709 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.1191. Min Act: -0.1700
Data Index: 4843339 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4629. Min Range: -5.4629
Max Act: 5.1191. Min Act: -0.1700
Data Index: 4916722 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19