Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.8343. Min Act: -0.1700
Data Index: 1003411 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.7718. Min Act: -0.1700
Data Index: 3345605 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.6468. Min Act: -0.1700
Data Index: 5557437 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5218. Min Act: -0.1700
Data Index: 7564631 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.4281. Min Act: -0.1700
Data Index: 6740009 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.4281. Min Act: -0.1700
Data Index: 3587444 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.4281. Min Act: -0.1700
Data Index: 7973598 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.4281. Min Act: -0.1700
Data Index: 5729434 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.3656. Min Act: -0.1700
Data Index: 417046 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.3968. Min Act: -0.1700
Data Index: 7505097 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.3031. Min Act: -0.1700
Data Index: 6838848 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.2406. Min Act: -0.1700
Data Index: 3168902 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.1781. Min Act: -0.1700
Data Index: 3872806 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.1781. Min Act: -0.1700
Data Index: 7813142 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.1468. Min Act: -0.1700
Data Index: 7038030 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.1156. Min Act: -0.1700
Data Index: 1151617 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.1156. Min Act: -0.1700
Data Index: 8222864 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.1468. Min Act: -0.1700
Data Index: 6270911 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.0843. Min Act: -0.1700
Data Index: 791054 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.0843. Min Act: -0.1700
Data Index: 7438730 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19