Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1571 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6930. Min Range: -10.6930
Max Act: 10.6930. Min Act: -0.1700
Data Index: 1792383 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6930. Min Range: -10.6930
Max Act: 10.5680. Min Act: -0.1700
Data Index: 1841959 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6930. Min Range: -10.6930
Max Act: 10.1305. Min Act: -0.1700
Data Index: 4142256 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6930. Min Range: -10.6930
Max Act: 10.0680. Min Act: -0.1700
Data Index: 3957724 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.9430. Min Act: -0.1700
Data Index: 4554750 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.8805. Min Act: -0.1700
Data Index: 1792394 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.8805. Min Act: -0.1700
Data Index: 3884825 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.8805. Min Act: -0.1700
Data Index: 5841226 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.8180. Min Act: -0.1700
Data Index: 5638012 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.8180. Min Act: -0.1700
Data Index: 7145280 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.8180. Min Act: -0.1700
Data Index: 3508273 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.6930. Min Act: -0.1700
Data Index: 4449307 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.6930. Min Act: -0.1700
Data Index: 3453092 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.6305. Min Act: -0.1700
Data Index: 630688 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.6305. Min Act: -0.1700
Data Index: 7812994 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.6305. Min Act: -0.1700
Data Index: 6143085 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.6305. Min Act: -0.1700
Data Index: 7319015 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.6305. Min Act: -0.1700
Data Index: 2685551 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.5680. Min Act: -0.1700
Data Index: 6628364 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6930. Min Range: -10.6930
Max Act: 9.5055. Min Act: -0.1700
Data Index: 5153031 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19