Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2140 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.8629. Min Act: -0.1700
Data Index: 776407 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.5504. Min Act: -0.1700
Data Index: 7616543 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.4254. Min Act: -0.1700
Data Index: 8046073 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.3316. Min Act: -0.1700
Data Index: 3966733 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.2379. Min Act: -0.1700
Data Index: 1190456 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.2691. Min Act: -0.1700
Data Index: 5273498 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.2379. Min Act: -0.1700
Data Index: 6936485 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1441. Min Act: -0.1700
Data Index: 6997365 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1754. Min Act: -0.1700
Data Index: 188296 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1754. Min Act: -0.1700
Data Index: 3846212 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1754. Min Act: -0.1700
Data Index: 3804634 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1754. Min Act: -0.1700
Data Index: 6151721 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1754. Min Act: -0.1700
Data Index: 2384160 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1441. Min Act: -0.1700
Data Index: 6170294 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1441. Min Act: -0.1700
Data Index: 134782 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1441. Min Act: -0.1700
Data Index: 8439909 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1128. Min Act: -0.1700
Data Index: 6939820 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1128. Min Act: -0.1700
Data Index: 2459171 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1128. Min Act: -0.1700
Data Index: 7267224 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.1128. Min Act: -0.1700
Data Index: 4187492 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19