Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4003 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3352. Min Range: -5.3352
Max Act: 5.3352. Min Act: -0.1700
Data Index: 3428493 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3352. Min Range: -5.3352
Max Act: 5.1790. Min Act: -0.1700
Data Index: 7466895 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3352. Min Range: -5.3352
Max Act: 5.0852. Min Act: -0.1700
Data Index: 3933232 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3352. Min Range: -5.3352
Max Act: 5.0227. Min Act: -0.1700
Data Index: 7994430 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.9602. Min Act: -0.1700
Data Index: 3202141 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.9602. Min Act: -0.1700
Data Index: 6887441 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.9290. Min Act: -0.1700
Data Index: 8512595 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8977. Min Act: -0.1700
Data Index: 1334309 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8977. Min Act: -0.1700
Data Index: 2370251 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8665. Min Act: -0.1700
Data Index: 6385444 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8665. Min Act: -0.1700
Data Index: 4977701 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8040. Min Act: -0.1700
Data Index: 6242473 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8352. Min Act: -0.1700
Data Index: 6424640 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8040. Min Act: -0.1700
Data Index: 2814791 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8040. Min Act: -0.1700
Data Index: 7759632 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.7727. Min Act: -0.1700
Data Index: 7324383 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8040. Min Act: -0.1700
Data Index: 7914178 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8040. Min Act: -0.1700
Data Index: 6750117 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.8040. Min Act: -0.1700
Data Index: 1981065 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3352. Min Range: -5.3352
Max Act: 4.7727. Min Act: -0.1700
Data Index: 3083750 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19