Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.7520. Min Act: -0.1700
Data Index: 7133676 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.5645. Min Act: -0.1700
Data Index: 2554647 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.5645. Min Act: -0.1700
Data Index: 1151080 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.5332. Min Act: -0.1700
Data Index: 2011471 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4707. Min Act: -0.1700
Data Index: 1705347 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4707. Min Act: -0.1700
Data Index: 3462815 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4707. Min Act: -0.1700
Data Index: 4227104 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4707. Min Act: -0.1700
Data Index: 8177657 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4395. Min Act: -0.1700
Data Index: 1637244 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4395. Min Act: -0.1700
Data Index: 5224496 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4395. Min Act: -0.1700
Data Index: 7727797 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4395. Min Act: -0.1700
Data Index: 7746264 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4395. Min Act: -0.1700
Data Index: 3394848 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4395. Min Act: -0.1700
Data Index: 3680441 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4082. Min Act: -0.1700
Data Index: 7663558 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.3770. Min Act: -0.1700
Data Index: 3111567 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4082. Min Act: -0.1700
Data Index: 4216757 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4395. Min Act: -0.1700
Data Index: 7887118 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.4082. Min Act: -0.1700
Data Index: 5767696 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7520. Min Range: -4.7520
Max Act: 4.3770. Min Act: -0.1700
Data Index: 6168859 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19