Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1464 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.8426. Min Act: -0.1700
Data Index: 6621642 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.7489. Min Act: -0.1700
Data Index: 6565311 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.3426. Min Act: -0.1700
Data Index: 5093696 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.2801. Min Act: -0.1700
Data Index: 8185457 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.3114. Min Act: -0.1700
Data Index: 7320740 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.2489. Min Act: -0.1700
Data Index: 680225 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.2801. Min Act: -0.1700
Data Index: 1377459 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.2489. Min Act: -0.1700
Data Index: 4975545 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.2489. Min Act: -0.1700
Data Index: 3133465 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.2801. Min Act: -0.1700
Data Index: 806364 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.2489. Min Act: -0.1700
Data Index: 6682998 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.1864. Min Act: -0.1700
Data Index: 8218292 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.2176. Min Act: -0.1700
Data Index: 3444463 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.2176. Min Act: -0.1700
Data Index: 7968516 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.1864. Min Act: -0.1700
Data Index: 2774456 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.2176. Min Act: -0.1700
Data Index: 7683860 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.1864. Min Act: -0.1700
Data Index: 5756900 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.1551. Min Act: -0.1700
Data Index: 7682207 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.1238. Min Act: -0.1700
Data Index: 1535042 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8426. Min Range: -4.8426
Max Act: 4.1551. Min Act: -0.1700
Data Index: 5601588 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19