Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.9201. Min Act: -0.1700
Data Index: 3012428 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.9045. Min Act: -0.1700
Data Index: 6684522 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.8732. Min Act: -0.1700
Data Index: 4850182 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.8263. Min Act: -0.1700
Data Index: 1975172 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.8107. Min Act: -0.1700
Data Index: 7984192 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.7169. Min Act: -0.1700
Data Index: 3483597 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.7325. Min Act: -0.1700
Data Index: 8262298 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.7325. Min Act: -0.1700
Data Index: 5687042 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.7012. Min Act: -0.1700
Data Index: 8757035 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6699. Min Act: -0.1700
Data Index: 1242727 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6856. Min Act: -0.1700
Data Index: 7529357 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6699. Min Act: -0.1700
Data Index: 7248129 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6543. Min Act: -0.1700
Data Index: 7328916 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6386. Min Act: -0.1700
Data Index: 6466379 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6230. Min Act: -0.1700
Data Index: 3760904 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6230. Min Act: -0.1700
Data Index: 5474443 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6230. Min Act: -0.1700
Data Index: 7238748 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6230. Min Act: -0.1700
Data Index: 768989 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6230. Min Act: -0.1700
Data Index: 4359102 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9201. Min Range: -3.9201
Max Act: 3.6073. Min Act: -0.1700
Data Index: 658264 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19