Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.2875. Min Act: -0.1700
Data Index: 347228 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.1550. Min Act: -0.1700
Data Index: 1449426 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.1384. Min Act: -0.1700
Data Index: 4616522 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.1384. Min Act: -0.1700
Data Index: 1312839 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.1384. Min Act: -0.1700
Data Index: 2418015 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.1217. Min Act: -0.1700
Data Index: 1219498 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.1217. Min Act: -0.1700
Data Index: 5283936 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.1049. Min Act: -0.1700
Data Index: 7315903 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.0882. Min Act: -0.1700
Data Index: 7915451 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.1049. Min Act: -0.1700
Data Index: 4606700 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.1049. Min Act: -0.1700
Data Index: 5369341 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.1049. Min Act: -0.1700
Data Index: 8010923 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.0882. Min Act: -0.1700
Data Index: 1106697 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.0714. Min Act: -0.1700
Data Index: 5080486 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.0714. Min Act: -0.1700
Data Index: 4804986 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.0546. Min Act: -0.1700
Data Index: 6826680 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.0714. Min Act: -0.1700
Data Index: 7821448 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.0882. Min Act: -0.1700
Data Index: 4841075 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.0714. Min Act: -0.1700
Data Index: 6769449 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2875. Min Range: -2.2875
Max Act: 2.0714. Min Act: -0.1700
Data Index: 432001 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19