Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5994 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.9966. Min Act: -0.1700
Data Index: 4129865 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.9966. Min Act: -0.1700
Data Index: 3945662 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.9653. Min Act: -0.1700
Data Index: 772252 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.8716. Min Act: -0.1700
Data Index: 4695036 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.6841. Min Act: -0.1700
Data Index: 7693562 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.6841. Min Act: -0.1700
Data Index: 115276 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.6841. Min Act: -0.1700
Data Index: 6435826 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.6216. Min Act: -0.1700
Data Index: 8318363 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.6216. Min Act: -0.1700
Data Index: 3763319 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.5903. Min Act: -0.1700
Data Index: 1213506 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.6528. Min Act: -0.1700
Data Index: 4631380 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.6216. Min Act: -0.1700
Data Index: 8160992 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.5903. Min Act: -0.1700
Data Index: 7181307 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.5278. Min Act: -0.1700
Data Index: 7681421 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.5278. Min Act: -0.1700
Data Index: 1282702 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.5278. Min Act: -0.1700
Data Index: 4782437 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.4966. Min Act: -0.1700
Data Index: 4670802 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.4653. Min Act: -0.1700
Data Index: 4982220 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.4966. Min Act: -0.1700
Data Index: 5250607 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9966. Min Range: -6.9966
Max Act: 6.4966. Min Act: -0.1700
Data Index: 4241059 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19