Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 649 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.9105. Min Act: -0.1700
Data Index: 8334736 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.9105. Min Act: -0.1700
Data Index: 841938 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.8167. Min Act: -0.1700
Data Index: 2959674 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.7854. Min Act: -0.1700
Data Index: 2668995 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.7542. Min Act: -0.1700
Data Index: 6202538 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.7229. Min Act: -0.1700
Data Index: 3396767 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.7229. Min Act: -0.1700
Data Index: 4824644 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.7229. Min Act: -0.1700
Data Index: 6702995 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6447. Min Act: -0.1700
Data Index: 7723656 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6603. Min Act: -0.1700
Data Index: 4891790 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6603. Min Act: -0.1700
Data Index: 8359252 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6603. Min Act: -0.1700
Data Index: 7016537 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6603. Min Act: -0.1700
Data Index: 1223048 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6290. Min Act: -0.1700
Data Index: 3013432 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6447. Min Act: -0.1700
Data Index: 2454294 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6447. Min Act: -0.1700
Data Index: 3564752 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6447. Min Act: -0.1700
Data Index: 3125438 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6134. Min Act: -0.1700
Data Index: 1059144 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6134. Min Act: -0.1700
Data Index: 373918 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9105. Min Range: -3.9105
Max Act: 3.6134. Min Act: -0.1700
Data Index: 2885236 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19