Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3795 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0762. Min Range: -7.0762
Max Act: 7.0762. Min Act: -0.1700
Data Index: 6155024 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.8887. Min Act: -0.1700
Data Index: 1864446 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.8262. Min Act: -0.1700
Data Index: 3775790 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.7949. Min Act: -0.1700
Data Index: 3974289 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.7949. Min Act: -0.1700
Data Index: 5862858 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.7637. Min Act: -0.1700
Data Index: 8667215 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.7637. Min Act: -0.1700
Data Index: 1199361 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.6699. Min Act: -0.1700
Data Index: 6871065 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.7012. Min Act: -0.1700
Data Index: 903749 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.7324. Min Act: -0.1700
Data Index: 7576503 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.6074. Min Act: -0.1700
Data Index: 3439014 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.6074. Min Act: -0.1700
Data Index: 6280324 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.6387. Min Act: -0.1700
Data Index: 3341767 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.5762. Min Act: -0.1700
Data Index: 3884396 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.5762. Min Act: -0.1700
Data Index: 8580093 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.5762. Min Act: -0.1700
Data Index: 8285090 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.5449. Min Act: -0.1700
Data Index: 3684610 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.5449. Min Act: -0.1700
Data Index: 5745341 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.5137. Min Act: -0.1700
Data Index: 3307338 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0762. Min Range: -7.0762
Max Act: 6.5137. Min Act: -0.1700
Data Index: 5535656 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19