Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2411 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6159. Min Range: -10.6159
Max Act: 10.6159. Min Act: -0.1700
Data Index: 2122618 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6159. Min Range: -10.6159
Max Act: 10.6159. Min Act: -0.1700
Data Index: 5591814 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6159. Min Range: -10.6159
Max Act: 10.3659. Min Act: -0.1700
Data Index: 3684897 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6159. Min Range: -10.6159
Max Act: 10.3034. Min Act: -0.1697
Data Index: 4741927 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6159. Min Range: -10.6159
Max Act: 10.2409. Min Act: -0.1700
Data Index: 1095812 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6159. Min Range: -10.6159
Max Act: 10.1784. Min Act: -0.1700
Data Index: 7709270 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6159. Min Range: -10.6159
Max Act: 10.1159. Min Act: -0.1700
Data Index: 6880445 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6159. Min Range: -10.6159
Max Act: 10.1159. Min Act: -0.1700
Data Index: 7916081 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6159. Min Range: -10.6159
Max Act: 10.1159. Min Act: -0.1700
Data Index: 2965847 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.9909. Min Act: -0.1700
Data Index: 8597758 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.9909. Min Act: -0.1700
Data Index: 3666987 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.9284. Min Act: -0.1700
Data Index: 6082798 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.9284. Min Act: -0.1700
Data Index: 1202564 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.8659. Min Act: -0.1700
Data Index: 2733677 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.8659. Min Act: -0.1700
Data Index: 1599885 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.9284. Min Act: -0.1700
Data Index: 1971244 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.8659. Min Act: -0.1700
Data Index: 7554341 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.8034. Min Act: -0.1700
Data Index: 5938894 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.7409. Min Act: -0.1700
Data Index: 8500880 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6159. Min Range: -10.6159
Max Act: 9.7409. Min Act: -0.1700
Data Index: 7047368 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19