Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2779 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1554. Min Range: -8.1554
Max Act: 8.1554. Min Act: -0.1700
Data Index: 2413463 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1554. Min Range: -8.1554
Max Act: 8.0929. Min Act: -0.1700
Data Index: 3888877 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.9679. Min Act: -0.1700
Data Index: 3606439 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.9054. Min Act: -0.1700
Data Index: 6881057 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.9054. Min Act: -0.1700
Data Index: 6046880 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.8429. Min Act: -0.1700
Data Index: 2518191 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.8429. Min Act: -0.1700
Data Index: 7889151 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.8429. Min Act: -0.1700
Data Index: 6262712 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.8429. Min Act: -0.1700
Data Index: 4474424 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7804. Min Act: -0.1700
Data Index: 3891455 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7804. Min Act: -0.1700
Data Index: 2917518 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7804. Min Act: -0.1700
Data Index: 4650278 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7804. Min Act: -0.1700
Data Index: 7084708 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7804. Min Act: -0.1700
Data Index: 8512390 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7804. Min Act: -0.1700
Data Index: 8223773 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7179. Min Act: -0.1700
Data Index: 3368985 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7179. Min Act: -0.1700
Data Index: 4105804 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7179. Min Act: -0.1700
Data Index: 2571853 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7179. Min Act: -0.1700
Data Index: 6431408 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1554. Min Range: -8.1554
Max Act: 7.7179. Min Act: -0.1700
Data Index: 291288 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19