Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1322. Min Range: -5.1322
Max Act: 5.1322. Min Act: -0.1700
Data Index: 4905987 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.9135. Min Act: -0.1700
Data Index: 2743198 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.9135. Min Act: -0.1700
Data Index: 3900567 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.9135. Min Act: -0.1700
Data Index: 2186687 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.8822. Min Act: -0.1700
Data Index: 2417131 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.8510. Min Act: -0.1700
Data Index: 8553331 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.8197. Min Act: -0.1700
Data Index: 4889718 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.8197. Min Act: -0.1700
Data Index: 1858828 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.8510. Min Act: -0.1700
Data Index: 1018263 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.8197. Min Act: -0.1700
Data Index: 4556886 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.7885. Min Act: -0.1700
Data Index: 5331619 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.7572. Min Act: -0.1700
Data Index: 1887177 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.7572. Min Act: -0.1700
Data Index: 4803189 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.7572. Min Act: -0.1700
Data Index: 2650144 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.7885. Min Act: -0.1700
Data Index: 4399872 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.7572. Min Act: -0.1700
Data Index: 6349679 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.6947. Min Act: -0.1700
Data Index: 2099601 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.7260. Min Act: -0.1700
Data Index: 2152540 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.7572. Min Act: -0.1700
Data Index: 3931643 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1322. Min Range: -5.1322
Max Act: 4.7260. Min Act: -0.1700
Data Index: 7705279 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19