Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6249 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.6431. Min Act: -0.1700
Data Index: 7411917 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.4868. Min Act: -0.1700
Data Index: 8462857 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.3931. Min Act: -0.1700
Data Index: 8602767 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.3931. Min Act: -0.1700
Data Index: 4995773 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.3618. Min Act: -0.1700
Data Index: 4201884 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.3306. Min Act: -0.1700
Data Index: 2796707 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.2993. Min Act: -0.1700
Data Index: 287406 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.2993. Min Act: -0.1700
Data Index: 629866 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.2368. Min Act: -0.1700
Data Index: 1741290 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.2368. Min Act: -0.1700
Data Index: 6337373 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.2368. Min Act: -0.1700
Data Index: 943622 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.2056. Min Act: -0.1700
Data Index: 8122384 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.2056. Min Act: -0.1700
Data Index: 4549748 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.2056. Min Act: -0.1700
Data Index: 4345693 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.1743. Min Act: -0.1700
Data Index: 6370236 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.1431. Min Act: -0.1700
Data Index: 3584224 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.1431. Min Act: -0.1700
Data Index: 3834080 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.1118. Min Act: -0.1700
Data Index: 8772151 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.1431. Min Act: -0.1700
Data Index: 1947014 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6431. Min Range: -5.6431
Max Act: 5.0493. Min Act: -0.1700
Data Index: 3800610 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19