Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4068 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1725. Min Range: -6.1725
Max Act: 6.1725. Min Act: -0.1700
Data Index: 2128071 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.9225. Min Act: -0.1700
Data Index: 8404038 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.8600. Min Act: -0.1700
Data Index: 4416334 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7975. Min Act: -0.1700
Data Index: 87547 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.8287. Min Act: -0.1700
Data Index: 7966876 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7662. Min Act: -0.1700
Data Index: 8048701 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7662. Min Act: -0.1700
Data Index: 3487759 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7350. Min Act: -0.1700
Data Index: 6103438 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7662. Min Act: -0.1700
Data Index: 6245118 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7350. Min Act: -0.1700
Data Index: 8138349 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7350. Min Act: -0.1700
Data Index: 6414005 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7037. Min Act: -0.1700
Data Index: 5518788 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7350. Min Act: -0.1700
Data Index: 5042917 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7037. Min Act: -0.1700
Data Index: 392594 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7037. Min Act: -0.1700
Data Index: 4738046 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.7037. Min Act: -0.1700
Data Index: 87246 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.6725. Min Act: -0.1700
Data Index: 8148451 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.6725. Min Act: -0.1700
Data Index: 3859098 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.6725. Min Act: -0.1700
Data Index: 3427353 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1725. Min Range: -6.1725
Max Act: 5.6725. Min Act: -0.1700
Data Index: 5653492 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19