Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 740 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.7439. Min Act: -0.1700
Data Index: 3941585 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.6501. Min Act: -0.1700
Data Index: 1187237 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.5251. Min Act: -0.1700
Data Index: 4878340 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.4626. Min Act: -0.1700
Data Index: 6597837 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.4314. Min Act: -0.1700
Data Index: 8381534 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3689. Min Act: -0.1700
Data Index: 3324814 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3689. Min Act: -0.1700
Data Index: 3745422 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3689. Min Act: -0.1700
Data Index: 3601974 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3376. Min Act: -0.1700
Data Index: 7957055 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3689. Min Act: -0.1700
Data Index: 2532573 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3376. Min Act: -0.1700
Data Index: 1636591 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3376. Min Act: -0.1700
Data Index: 8413182 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3376. Min Act: -0.1700
Data Index: 5942268 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3376. Min Act: -0.1700
Data Index: 6765465 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3376. Min Act: -0.1700
Data Index: 110913 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3064. Min Act: -0.1700
Data Index: 7177005 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3376. Min Act: -0.1700
Data Index: 3625850 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3064. Min Act: -0.1700
Data Index: 1856975 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.3064. Min Act: -0.1700
Data Index: 1357104 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7439. Min Range: -5.7439
Max Act: 5.2751. Min Act: -0.1700
Data Index: 7763041 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19