Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5439 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7429. Min Range: -8.7429
Max Act: 8.7429. Min Act: -0.1700
Data Index: 5176855 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7429. Min Range: -8.7429
Max Act: 8.1804. Min Act: -0.1700
Data Index: 6331618 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7429. Min Range: -8.7429
Max Act: 8.1179. Min Act: -0.1700
Data Index: 7749126 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7429. Min Range: -8.7429
Max Act: 8.0554. Min Act: -0.1700
Data Index: 1827423 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.9929. Min Act: -0.1700
Data Index: 4868881 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.9929. Min Act: -0.1700
Data Index: 2745836 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.9929. Min Act: -0.1700
Data Index: 7675518 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.9304. Min Act: -0.1700
Data Index: 7077420 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.9304. Min Act: -0.1700
Data Index: 3651831 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8679. Min Act: -0.1700
Data Index: 3051795 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8679. Min Act: -0.1700
Data Index: 7438074 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8679. Min Act: -0.1700
Data Index: 6005036 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8679. Min Act: -0.1700
Data Index: 1231993 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8679. Min Act: -0.1700
Data Index: 604015 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8679. Min Act: -0.1700
Data Index: 8479602 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8367. Min Act: -0.1700
Data Index: 704235 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8367. Min Act: -0.1700
Data Index: 2971186 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8054. Min Act: -0.1700
Data Index: 1686467 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8054. Min Act: -0.1700
Data Index: 8049141 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7429. Min Range: -8.7429
Max Act: 7.8054. Min Act: -0.1698
Data Index: 6229041 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19