Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.7681. Min Act: -0.1700
Data Index: 4647950 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.7368. Min Act: -0.1700
Data Index: 3752493 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.6118. Min Act: -0.1700
Data Index: 6890624 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.5806. Min Act: -0.1700
Data Index: 2825173 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.5806. Min Act: -0.1700
Data Index: 310081 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.5493. Min Act: -0.1700
Data Index: 5360209 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.5493. Min Act: -0.1700
Data Index: 6873886 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.4868. Min Act: -0.1700
Data Index: 4336534 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.4868. Min Act: -0.1700
Data Index: 6183158 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.4556. Min Act: -0.1700
Data Index: 6157351 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.4556. Min Act: -0.1700
Data Index: 5474114 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.3931. Min Act: -0.1700
Data Index: 8762012 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.2993. Min Act: -0.1700
Data Index: 3226161 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.3306. Min Act: -0.1700
Data Index: 5498744 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.2993. Min Act: -0.1700
Data Index: 7058656 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.2681. Min Act: -0.1700
Data Index: 5006034 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.2368. Min Act: -0.1700
Data Index: 6592767 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.2368. Min Act: -0.1700
Data Index: 7798739 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.2368. Min Act: -0.1700
Data Index: 8124500 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7681. Min Range: -7.7681
Max Act: 7.2056. Min Act: -0.1700
Data Index: 697905 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19