Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5700 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0431. Min Range: -4.0431
Max Act: 4.0431. Min Act: -0.1700
Data Index: 3472094 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.9805. Min Act: -0.1700
Data Index: 7166760 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0431. Min Range: -4.0431
Max Act: 4.0118. Min Act: -0.1700
Data Index: 1576768 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0431. Min Range: -4.0431
Max Act: 4.0118. Min Act: -0.1700
Data Index: 4240629 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.9493. Min Act: -0.1700
Data Index: 650816 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.9180. Min Act: -0.1700
Data Index: 7005439 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.9180. Min Act: -0.1700
Data Index: 4632428 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.9180. Min Act: -0.1700
Data Index: 4240627 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8867. Min Act: -0.1700
Data Index: 3630861 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8867. Min Act: -0.1700
Data Index: 6497430 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8867. Min Act: -0.1700
Data Index: 3751993 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8867. Min Act: -0.1700
Data Index: 8671171 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8555. Min Act: -0.1700
Data Index: 910772 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8555. Min Act: -0.1700
Data Index: 7035709 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8555. Min Act: -0.1700
Data Index: 2911216 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8242. Min Act: -0.1700
Data Index: 4374073 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8242. Min Act: -0.1700
Data Index: 3457789 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8242. Min Act: -0.1700
Data Index: 2686493 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8242. Min Act: -0.1700
Data Index: 7874204 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0431. Min Range: -4.0431
Max Act: 3.8555. Min Act: -0.1700
Data Index: 3960942 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19