Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1210. Min Range: -8.1210
Max Act: 8.1210. Min Act: -0.1700
Data Index: 3937503 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.7460. Min Act: -0.1700
Data Index: 8512767 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.8085. Min Act: -0.1700
Data Index: 2933777 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.7460. Min Act: -0.1700
Data Index: 6801825 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.7460. Min Act: -0.1700
Data Index: 3449730 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.6835. Min Act: -0.1700
Data Index: 8686960 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.6210. Min Act: -0.1700
Data Index: 7825248 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.6835. Min Act: -0.1700
Data Index: 434723 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.6835. Min Act: -0.1700
Data Index: 7028221 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.6210. Min Act: -0.1700
Data Index: 8181697 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.6210. Min Act: -0.1700
Data Index: 4253658 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.6210. Min Act: -0.1700
Data Index: 6957086 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.6210. Min Act: -0.1700
Data Index: 7701078 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.6210. Min Act: -0.1700
Data Index: 5300109 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.5585. Min Act: -0.1700
Data Index: 4957722 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.5585. Min Act: -0.1700
Data Index: 8370893 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.5585. Min Act: -0.1700
Data Index: 6673323 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.4960. Min Act: -0.1700
Data Index: 31624 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.4960. Min Act: -0.1700
Data Index: 5390944 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1210. Min Range: -8.1210
Max Act: 7.4960. Min Act: -0.1700
Data Index: 2920580 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19