Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3857. Min Range: -8.3857
Max Act: 8.3857. Min Act: -0.1700
Data Index: 8402414 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3857. Min Range: -8.3857
Max Act: 8.0107. Min Act: -0.1700
Data Index: 2838810 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3857. Min Range: -8.3857
Max Act: 8.0107. Min Act: -0.1700
Data Index: 4784509 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.9482. Min Act: -0.1700
Data Index: 4608476 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.7607. Min Act: -0.1700
Data Index: 8668477 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.6982. Min Act: -0.1700
Data Index: 4547179 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.6669. Min Act: -0.1700
Data Index: 7862463 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.6044. Min Act: -0.1700
Data Index: 4110461 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.5419. Min Act: -0.1700
Data Index: 3994797 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.5732. Min Act: -0.1700
Data Index: 4147035 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.5419. Min Act: -0.1700
Data Index: 3115310 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.5419. Min Act: -0.1700
Data Index: 1092854 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.5107. Min Act: -0.1700
Data Index: 6077927 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.5419. Min Act: -0.1700
Data Index: 5325085 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.5419. Min Act: -0.1700
Data Index: 1600324 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.5107. Min Act: -0.1700
Data Index: 918327 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.5107. Min Act: -0.1700
Data Index: 3361402 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.4794. Min Act: -0.1700
Data Index: 844922 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.4482. Min Act: -0.1700
Data Index: 284781 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3857. Min Range: -8.3857
Max Act: 7.4482. Min Act: -0.1700
Data Index: 6173310 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19