Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4226 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3456. Min Range: -6.3456
Max Act: 6.3456. Min Act: -0.1700
Data Index: 3094297 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.8769. Min Act: -0.1700
Data Index: 5410170 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.8144. Min Act: -0.1700
Data Index: 2156721 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.7831. Min Act: -0.1700
Data Index: 3321962 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.7831. Min Act: -0.1700
Data Index: 5027044 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.7519. Min Act: -0.1700
Data Index: 174244 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.7206. Min Act: -0.1700
Data Index: 3002719 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.7206. Min Act: -0.1700
Data Index: 7216172 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6894. Min Act: -0.1700
Data Index: 4289886 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6894. Min Act: -0.1700
Data Index: 2257398 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6581. Min Act: -0.1700
Data Index: 5745910 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6894. Min Act: -0.1700
Data Index: 4519450 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6894. Min Act: -0.1700
Data Index: 7827552 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6894. Min Act: -0.1700
Data Index: 439185 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6581. Min Act: -0.1700
Data Index: 5335251 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6581. Min Act: -0.1700
Data Index: 2525770 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6581. Min Act: -0.1700
Data Index: 1977227 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.5956. Min Act: -0.1700
Data Index: 7889846 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6269. Min Act: -0.1700
Data Index: 4702924 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3456. Min Range: -6.3456
Max Act: 5.6269. Min Act: -0.1700
Data Index: 3775564 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19