Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2235 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2072. Min Range: -7.2072
Max Act: 7.2072. Min Act: -0.1700
Data Index: 6257588 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.8947. Min Act: -0.1700
Data Index: 5952828 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.8634. Min Act: -0.1700
Data Index: 1538293 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.8634. Min Act: -0.1700
Data Index: 3697814 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.8322. Min Act: -0.1700
Data Index: 5096491 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.8009. Min Act: -0.1700
Data Index: 8229050 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.8009. Min Act: -0.1700
Data Index: 6854378 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.7697. Min Act: -0.1700
Data Index: 1065230 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.7384. Min Act: -0.1700
Data Index: 6803647 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.7384. Min Act: -0.1700
Data Index: 5772482 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.7072. Min Act: -0.1700
Data Index: 1530178 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.7072. Min Act: -0.1700
Data Index: 6470577 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.7072. Min Act: -0.1700
Data Index: 8490811 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.6759. Min Act: -0.1700
Data Index: 8456249 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.7072. Min Act: -0.1700
Data Index: 5027852 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.6759. Min Act: -0.1700
Data Index: 7236925 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.6759. Min Act: -0.1700
Data Index: 5036414 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.6447. Min Act: -0.1700
Data Index: 3029282 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.6134. Min Act: -0.1700
Data Index: 745105 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2072. Min Range: -7.2072
Max Act: 6.5822. Min Act: -0.1700
Data Index: 7587937 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19