Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3630. Min Range: -4.3630
Max Act: 4.3630. Min Act: -0.1700
Data Index: 5025675 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3630. Min Range: -4.3630
Max Act: 4.0817. Min Act: -0.1700
Data Index: 763949 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3630. Min Range: -4.3630
Max Act: 4.0191. Min Act: -0.1700
Data Index: 2601444 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3630. Min Range: -4.3630
Max Act: 4.0504. Min Act: -0.1700
Data Index: 1972538 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.9566. Min Act: -0.1700
Data Index: 6195910 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.9879. Min Act: -0.1700
Data Index: 7627782 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.9254. Min Act: -0.1700
Data Index: 191991 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.8628. Min Act: -0.1700
Data Index: 6039730 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.8628. Min Act: -0.1700
Data Index: 7470511 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.8941. Min Act: -0.1700
Data Index: 7826114 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.8316. Min Act: -0.1700
Data Index: 8344411 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.8003. Min Act: -0.1700
Data Index: 278968 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.8003. Min Act: -0.1700
Data Index: 2209808 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.7377. Min Act: -0.1700
Data Index: 1723024 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.7690. Min Act: -0.1700
Data Index: 2295339 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.7377. Min Act: -0.1700
Data Index: 8134721 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.7690. Min Act: -0.1700
Data Index: 3359168 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.7690. Min Act: -0.1700
Data Index: 3158994 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.7690. Min Act: -0.1700
Data Index: 2712891 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3630. Min Range: -4.3630
Max Act: 3.7690. Min Act: -0.1700
Data Index: 5624012 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19