Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.5010. Min Act: -0.1700
Data Index: 2860301 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.3760. Min Act: -0.1700
Data Index: 6617715 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.3760. Min Act: -0.1700
Data Index: 1022168 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.3447. Min Act: -0.1700
Data Index: 8501949 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.2510. Min Act: -0.1700
Data Index: 94810 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.2510. Min Act: -0.1700
Data Index: 3956590 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1572. Min Act: -0.1700
Data Index: 127355 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1260. Min Act: -0.1700
Data Index: 3105076 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1260. Min Act: -0.1700
Data Index: 4805589 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1572. Min Act: -0.1700
Data Index: 3892767 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1260. Min Act: -0.1700
Data Index: 1510782 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1260. Min Act: -0.1700
Data Index: 6579612 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0947. Min Act: -0.1700
Data Index: 866136 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1260. Min Act: -0.1700
Data Index: 133253 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0947. Min Act: -0.1700
Data Index: 6194955 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0635. Min Act: -0.1700
Data Index: 6485268 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0635. Min Act: -0.1700
Data Index: 7499646 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0635. Min Act: -0.1700
Data Index: 865091 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0635. Min Act: -0.1700
Data Index: 6040813 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0635. Min Act: -0.1700
Data Index: 8746368 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19