Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4325 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3757. Min Range: -10.3757
Max Act: 10.3757. Min Act: -0.1700
Data Index: 5109293 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3757. Min Range: -10.3757
Max Act: 10.2507. Min Act: -0.1700
Data Index: 1957894 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3757. Min Range: -10.3757
Max Act: 10.2507. Min Act: -0.1700
Data Index: 4386874 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.7507. Min Act: -0.1700
Data Index: 7799017 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.6882. Min Act: -0.1700
Data Index: 534307 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.6882. Min Act: -0.1700
Data Index: 4622170 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.6257. Min Act: -0.1700
Data Index: 2222841 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.5632. Min Act: -0.1700
Data Index: 4896486 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.5632. Min Act: -0.1700
Data Index: 7206117 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.5632. Min Act: -0.1700
Data Index: 8501376 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.5632. Min Act: -0.1700
Data Index: 7494967 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.3757. Min Act: -0.1700
Data Index: 3947364 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.3757. Min Act: -0.1700
Data Index: 2608832 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.3132. Min Act: -0.1700
Data Index: 5361138 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.2507. Min Act: -0.1700
Data Index: 2524186 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.2507. Min Act: -0.1700
Data Index: 1056934 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.2507. Min Act: -0.1700
Data Index: 3685123 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.2507. Min Act: -0.1700
Data Index: 562529 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.2507. Min Act: -0.1700
Data Index: 7491973 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3757. Min Range: -10.3757
Max Act: 9.1882. Min Act: -0.1700
Data Index: 6498280 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19