Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 387 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3666. Min Range: -10.3666
Max Act: 10.3666. Min Act: -0.1700
Data Index: 401375 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3666. Min Range: -10.3666
Max Act: 10.3666. Min Act: -0.1700
Data Index: 401376 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.9916. Min Act: -0.1700
Data Index: 228583 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.7416. Min Act: -0.1700
Data Index: 8651668 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.6791. Min Act: -0.1700
Data Index: 1610863 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.6791. Min Act: -0.1700
Data Index: 1414247 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.5541. Min Act: -0.1700
Data Index: 835889 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.4291. Min Act: -0.1700
Data Index: 7736031 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.3666. Min Act: -0.1700
Data Index: 1194452 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.3041. Min Act: -0.1700
Data Index: 5109306 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.3041. Min Act: -0.1700
Data Index: 4334593 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.2416. Min Act: -0.1700
Data Index: 2374780 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.2416. Min Act: -0.1700
Data Index: 8693781 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.2416. Min Act: -0.1700
Data Index: 3372275 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.1166. Min Act: -0.1700
Data Index: 1607438 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.1791. Min Act: -0.1700
Data Index: 2838771 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.1166. Min Act: -0.1700
Data Index: 6047489 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.1166. Min Act: -0.1700
Data Index: 8785723 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.0541. Min Act: -0.1700
Data Index: 973976 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3666. Min Range: -10.3666
Max Act: 9.0541. Min Act: -0.1700
Data Index: 6674972 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19