Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.9264. Min Act: -0.1700
Data Index: 4239908 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.9576. Min Act: -0.1700
Data Index: 8491531 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.8951. Min Act: -0.1700
Data Index: 8108312 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.8639. Min Act: -0.1700
Data Index: 6058157 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.8639. Min Act: -0.1700
Data Index: 6428059 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.8951. Min Act: -0.1700
Data Index: 977737 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.8326. Min Act: -0.1700
Data Index: 1306256 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.8639. Min Act: -0.1700
Data Index: 2892417 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.7701. Min Act: -0.1700
Data Index: 1727528 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.7701. Min Act: -0.1700
Data Index: 7859505 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.7389. Min Act: -0.1700
Data Index: 1543840 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.7389. Min Act: -0.1700
Data Index: 3006993 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.7389. Min Act: -0.1700
Data Index: 7708660 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.7389. Min Act: -0.1700
Data Index: 7793759 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.7076. Min Act: -0.1700
Data Index: 7683386 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.6764. Min Act: -0.1700
Data Index: 5537431 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.7076. Min Act: -0.1700
Data Index: 4504547 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.6764. Min Act: -0.1700
Data Index: 3683711 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.6451. Min Act: -0.1700
Data Index: 8566143 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9576. Min Range: -5.9576
Max Act: 5.6139. Min Act: -0.1700
Data Index: 1629405 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19