Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 731 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1166. Min Range: -8.1166
Max Act: 8.1166. Min Act: -0.1700
Data Index: 6452864 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1166. Min Range: -8.1166
Max Act: 8.0541. Min Act: -0.1700
Data Index: 8019309 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.8041. Min Act: -0.1700
Data Index: 4105363 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.7416. Min Act: -0.1700
Data Index: 8482410 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.7416. Min Act: -0.1700
Data Index: 5435821 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.7416. Min Act: -0.1700
Data Index: 2202253 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.7416. Min Act: -0.1700
Data Index: 5183756 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.6791. Min Act: -0.1700
Data Index: 4345187 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.6791. Min Act: -0.1700
Data Index: 4030099 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.6791. Min Act: -0.1700
Data Index: 2240329 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.5541. Min Act: -0.1700
Data Index: 3957817 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.5541. Min Act: -0.1700
Data Index: 6997598 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.5229. Min Act: -0.1700
Data Index: 3968358 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.4916. Min Act: -0.1700
Data Index: 2514251 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.5229. Min Act: -0.1700
Data Index: 3278500 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.5229. Min Act: -0.1700
Data Index: 1951901 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.5229. Min Act: -0.1700
Data Index: 5206419 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.5229. Min Act: -0.1700
Data Index: 4926859 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.5229. Min Act: -0.1700
Data Index: 1385870 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1166. Min Range: -8.1166
Max Act: 7.4604. Min Act: -0.1700
Data Index: 5231019 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19