Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3651 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3527. Min Range: -5.3527
Max Act: 5.3527. Min Act: -0.1700
Data Index: 6810947 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3527. Min Range: -5.3527
Max Act: 5.2902. Min Act: -0.1700
Data Index: 1797010 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3527. Min Range: -5.3527
Max Act: 5.2277. Min Act: -0.1700
Data Index: 5423113 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3527. Min Range: -5.3527
Max Act: 5.1340. Min Act: -0.1700
Data Index: 6718778 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3527. Min Range: -5.3527
Max Act: 5.1027. Min Act: -0.1700
Data Index: 3230810 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3527. Min Range: -5.3527
Max Act: 5.1027. Min Act: -0.1700
Data Index: 3765627 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3527. Min Range: -5.3527
Max Act: 5.0090. Min Act: -0.1700
Data Index: 6699520 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3527. Min Range: -5.3527
Max Act: 5.0090. Min Act: -0.1700
Data Index: 6899417 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9465. Min Act: -0.1700
Data Index: 5085340 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9777. Min Act: -0.1700
Data Index: 845092 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9465. Min Act: -0.1700
Data Index: 353590 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9465. Min Act: -0.1700
Data Index: 3753024 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9465. Min Act: -0.1700
Data Index: 122011 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9152. Min Act: -0.1700
Data Index: 6325374 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9152. Min Act: -0.1700
Data Index: 6971221 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9152. Min Act: -0.1700
Data Index: 7515814 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9152. Min Act: -0.1700
Data Index: 1976239 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9152. Min Act: -0.1700
Data Index: 1231526 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9152. Min Act: -0.1700
Data Index: 8490933 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3527. Min Range: -5.3527
Max Act: 4.9152. Min Act: -0.1700
Data Index: 5112319 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19