Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.8085. Min Act: -0.1700
Data Index: 4926459 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.8085. Min Act: -0.1700
Data Index: 3087272 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.7772. Min Act: -0.1700
Data Index: 5512080 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.7147. Min Act: -0.1700
Data Index: 2032278 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.7147. Min Act: -0.1700
Data Index: 3195068 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6835. Min Act: -0.1700
Data Index: 1281716 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6522. Min Act: -0.1700
Data Index: 7637844 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6210. Min Act: -0.1700
Data Index: 6893140 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6210. Min Act: -0.1700
Data Index: 2652183 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.6210. Min Act: -0.1700
Data Index: 900857 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.5897. Min Act: -0.1700
Data Index: 6733403 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.5585. Min Act: -0.1700
Data Index: 4512042 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.5585. Min Act: -0.1700
Data Index: 1236353 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4960. Min Act: -0.1700
Data Index: 2978446 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4960. Min Act: -0.1700
Data Index: 8231407 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4960. Min Act: -0.1700
Data Index: 2751868 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4960. Min Act: -0.1700
Data Index: 4259728 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4647. Min Act: -0.1700
Data Index: 8711979 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4647. Min Act: -0.1700
Data Index: 6328505 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8085. Min Range: -4.8085
Max Act: 4.4335. Min Act: -0.1700
Data Index: 4338600 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19