Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1612 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0196. Min Range: -6.0196
Max Act: 6.0196. Min Act: -0.1700
Data Index: 1484544 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.9258. Min Act: -0.1700
Data Index: 7055756 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.9571. Min Act: -0.1700
Data Index: 2773492 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.9883. Min Act: -0.1700
Data Index: 1585412 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.8008. Min Act: -0.1700
Data Index: 1197466 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7696. Min Act: -0.1700
Data Index: 6136928 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7696. Min Act: -0.1700
Data Index: 371630 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6758. Min Act: -0.1700
Data Index: 7979492 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.7071. Min Act: -0.1700
Data Index: 5167973 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6758. Min Act: -0.1700
Data Index: 1068094 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6758. Min Act: -0.1700
Data Index: 7533698 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6446. Min Act: -0.1700
Data Index: 8582018 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6446. Min Act: -0.1700
Data Index: 5401337 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6758. Min Act: -0.1700
Data Index: 6017763 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6446. Min Act: -0.1700
Data Index: 7689960 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6133. Min Act: -0.1700
Data Index: 2363924 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6133. Min Act: -0.1700
Data Index: 7885079 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6133. Min Act: -0.1700
Data Index: 1368794 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.6133. Min Act: -0.1700
Data Index: 5707176 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0196. Min Range: -6.0196
Max Act: 5.5821. Min Act: -0.1700
Data Index: 5922559 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19