Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0185. Min Range: -6.0185
Max Act: 6.0185. Min Act: -0.1700
Data Index: 1402068 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.9560. Min Act: -0.1700
Data Index: 7076555 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.9248. Min Act: -0.1700
Data Index: 1833770 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.9560. Min Act: -0.1700
Data Index: 774840 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.9248. Min Act: -0.1700
Data Index: 4518896 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.9248. Min Act: -0.1700
Data Index: 4249705 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.8935. Min Act: -0.1700
Data Index: 7230264 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.8623. Min Act: -0.1700
Data Index: 961881 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.8310. Min Act: -0.1700
Data Index: 3997908 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.7998. Min Act: -0.1700
Data Index: 7343795 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.8623. Min Act: -0.1700
Data Index: 961859 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.8310. Min Act: -0.1700
Data Index: 1632757 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.7998. Min Act: -0.1700
Data Index: 8057300 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.7685. Min Act: -0.1700
Data Index: 7461390 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.7685. Min Act: -0.1700
Data Index: 3384181 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.7685. Min Act: -0.1700
Data Index: 1707939 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.7373. Min Act: -0.1700
Data Index: 4511709 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.7373. Min Act: -0.1700
Data Index: 961880 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.7373. Min Act: -0.1700
Data Index: 706218 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0185. Min Range: -6.0185
Max Act: 5.7685. Min Act: -0.1700
Data Index: 4639519 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19