Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1814. Min Range: -4.1814
Max Act: 4.1814. Min Act: -0.1700
Data Index: 7729885 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1814. Min Range: -4.1814
Max Act: 4.0876. Min Act: -0.1700
Data Index: 3555545 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1814. Min Range: -4.1814
Max Act: 4.0876. Min Act: -0.1700
Data Index: 4853775 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1814. Min Range: -4.1814
Max Act: 4.0251. Min Act: -0.1700
Data Index: 717509 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9938. Min Act: -0.1700
Data Index: 8180808 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9938. Min Act: -0.1700
Data Index: 4046540 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9938. Min Act: -0.1700
Data Index: 612985 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9626. Min Act: -0.1700
Data Index: 988131 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9626. Min Act: -0.1700
Data Index: 1334550 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9313. Min Act: -0.1700
Data Index: 8736367 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9313. Min Act: -0.1700
Data Index: 1867843 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9313. Min Act: -0.1700
Data Index: 2156224 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9313. Min Act: -0.1700
Data Index: 8679537 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9000. Min Act: -0.1700
Data Index: 1402635 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9313. Min Act: -0.1700
Data Index: 8103008 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9000. Min Act: -0.1700
Data Index: 5104698 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9000. Min Act: -0.1700
Data Index: 1602180 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9313. Min Act: -0.1700
Data Index: 6558739 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9000. Min Act: -0.1700
Data Index: 7733562 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1814. Min Range: -4.1814
Max Act: 3.9000. Min Act: -0.1700
Data Index: 8103007 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19