Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1115 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3566. Min Range: -7.3566
Max Act: 7.3566. Min Act: -0.1700
Data Index: 649 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.9816. Min Act: -0.1700
Data Index: 3272185 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.9504. Min Act: -0.1700
Data Index: 6459621 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.9191. Min Act: -0.1700
Data Index: 8031447 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.6691. Min Act: -0.1700
Data Index: 5029842 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.5129. Min Act: -0.1700
Data Index: 4813433 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.5441. Min Act: -0.1700
Data Index: 783572 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.4816. Min Act: -0.1700
Data Index: 3303215 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.4191. Min Act: -0.1700
Data Index: 3179408 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.3879. Min Act: -0.1700
Data Index: 1559571 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.2941. Min Act: -0.1700
Data Index: 2503655 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.2941. Min Act: -0.1700
Data Index: 8404130 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.2941. Min Act: -0.1700
Data Index: 7410276 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.2941. Min Act: -0.1700
Data Index: 7507140 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.2316. Min Act: -0.1700
Data Index: 4633026 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.2629. Min Act: -0.1700
Data Index: 7228045 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.2316. Min Act: -0.1700
Data Index: 5012985 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.2004. Min Act: -0.1700
Data Index: 2935731 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.2316. Min Act: -0.1700
Data Index: 1996192 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3566. Min Range: -7.3566
Max Act: 6.2629. Min Act: -0.1700
Data Index: 4253666 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19