Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.6531. Min Act: -0.1700
Data Index: 8373167 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.4969. Min Act: -0.1700
Data Index: 1070118 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.4344. Min Act: -0.1700
Data Index: 8479398 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.4344. Min Act: -0.1700
Data Index: 7576419 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.4031. Min Act: -0.1700
Data Index: 8391220 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.4031. Min Act: -0.1700
Data Index: 107590 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.2469. Min Act: -0.1700
Data Index: 5905877 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.2156. Min Act: -0.1700
Data Index: 3000504 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.2156. Min Act: -0.1700
Data Index: 8632584 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.1531. Min Act: -0.1700
Data Index: 5822724 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.1844. Min Act: -0.1700
Data Index: 7923474 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.1219. Min Act: -0.1700
Data Index: 7999428 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.1219. Min Act: -0.1700
Data Index: 3094352 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.0906. Min Act: -0.1700
Data Index: 7473823 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6531. Min Range: -6.6531
Max Act: 6.0906. Min Act: -0.1700
Data Index: 203615 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6531. Min Range: -6.6531
Max Act: 5.9969. Min Act: -0.1700
Data Index: 7109489 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6531. Min Range: -6.6531
Max Act: 5.9969. Min Act: -0.1700
Data Index: 6134093 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6531. Min Range: -6.6531
Max Act: 5.9969. Min Act: -0.1700
Data Index: 8687275 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6531. Min Range: -6.6531
Max Act: 5.9969. Min Act: -0.1700
Data Index: 7058824 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6531. Min Range: -6.6531
Max Act: 5.9656. Min Act: -0.1700
Data Index: 2070581 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19