Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.4228. Min Act: -0.1700
Data Index: 5438165 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.2353. Min Act: -0.1700
Data Index: 1213941 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.1727. Min Act: -0.1700
Data Index: 8136289 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.1727. Min Act: -0.1700
Data Index: 4603492 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.1102. Min Act: -0.1700
Data Index: 622411 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.1102. Min Act: -0.1700
Data Index: 382497 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.1102. Min Act: -0.1700
Data Index: 6360716 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.1102. Min Act: -0.1700
Data Index: 2442114 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.0790. Min Act: -0.1700
Data Index: 8754161 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.0790. Min Act: -0.1700
Data Index: 4169158 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.0477. Min Act: -0.1700
Data Index: 1010594 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.1102. Min Act: -0.1700
Data Index: 1624572 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.0165. Min Act: -0.1700
Data Index: 3321198 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.0477. Min Act: -0.1700
Data Index: 4015108 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.0477. Min Act: -0.1700
Data Index: 1774037 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.0165. Min Act: -0.1700
Data Index: 6491850 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.0165. Min Act: -0.1700
Data Index: 1321350 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.0477. Min Act: -0.1700
Data Index: 7457578 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4228. Min Range: -4.4228
Max Act: 3.9852. Min Act: -0.1700
Data Index: 3507437 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4228. Min Range: -4.4228
Max Act: 4.0165. Min Act: -0.1700
Data Index: 865336 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19