Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.3176. Min Act: -0.1700
Data Index: 410686 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.2864. Min Act: -0.1700
Data Index: 3949882 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.2551. Min Act: -0.1700
Data Index: 4506549 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.2239. Min Act: -0.1700
Data Index: 6835796 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.2551. Min Act: -0.1700
Data Index: 8055712 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.1926. Min Act: -0.1700
Data Index: 6548533 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.1926. Min Act: -0.1700
Data Index: 6946910 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.1926. Min Act: -0.1700
Data Index: 93712 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.0989. Min Act: -0.1700
Data Index: 4293975 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.1301. Min Act: -0.1700
Data Index: 5579274 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.0989. Min Act: -0.1700
Data Index: 2401443 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.1301. Min Act: -0.1700
Data Index: 4807818 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.0676. Min Act: -0.1700
Data Index: 8675933 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.0364. Min Act: -0.1700
Data Index: 3801944 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.0051. Min Act: -0.1700
Data Index: 664729 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3176. Min Range: -7.3176
Max Act: 7.0051. Min Act: -0.1700
Data Index: 395295 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3176. Min Range: -7.3176
Max Act: 6.9739. Min Act: -0.1700
Data Index: 1322407 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3176. Min Range: -7.3176
Max Act: 6.9739. Min Act: -0.1700
Data Index: 4935254 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3176. Min Range: -7.3176
Max Act: 6.9426. Min Act: -0.1700
Data Index: 279004 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3176. Min Range: -7.3176
Max Act: 6.9426. Min Act: -0.1700
Data Index: 5827735 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19