Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5087 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7389. Min Range: -8.7389
Max Act: 8.7389. Min Act: -0.1700
Data Index: 8059577 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7389. Min Range: -8.7389
Max Act: 8.3014. Min Act: -0.1700
Data Index: 8502940 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7389. Min Range: -8.7389
Max Act: 8.1764. Min Act: -0.1700
Data Index: 6942063 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.9889. Min Act: -0.1700
Data Index: 7582556 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.9889. Min Act: -0.1700
Data Index: 4874331 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.9889. Min Act: -0.1700
Data Index: 3415898 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.9576. Min Act: -0.1700
Data Index: 8486269 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.9576. Min Act: -0.1700
Data Index: 6897509 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.8951. Min Act: -0.1700
Data Index: 3875400 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.8326. Min Act: -0.1700
Data Index: 6311824 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.8326. Min Act: -0.1700
Data Index: 949563 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.8639. Min Act: -0.1700
Data Index: 7103753 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.8326. Min Act: -0.1700
Data Index: 4358359 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.8326. Min Act: -0.1700
Data Index: 7518260 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.7076. Min Act: -0.1700
Data Index: 1734926 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.6764. Min Act: -0.1700
Data Index: 72496 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.6451. Min Act: -0.1700
Data Index: 4244954 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.6451. Min Act: -0.1700
Data Index: 3104766 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.6451. Min Act: -0.1700
Data Index: 6197206 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7389. Min Range: -8.7389
Max Act: 7.6139. Min Act: -0.1700
Data Index: 3838655 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19