Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5229. Min Range: -6.5229
Max Act: 6.5229. Min Act: -0.1700
Data Index: 3913212 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5229. Min Range: -6.5229
Max Act: 6.0541. Min Act: -0.1700
Data Index: 645907 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.9604. Min Act: -0.1700
Data Index: 7100148 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.9291. Min Act: -0.1700
Data Index: 6288908 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.8666. Min Act: -0.1700
Data Index: 8522210 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.8354. Min Act: -0.1700
Data Index: 685090 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.8041. Min Act: -0.1700
Data Index: 2655028 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.8041. Min Act: -0.1700
Data Index: 7237307 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.7729. Min Act: -0.1700
Data Index: 3109377 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.7104. Min Act: -0.1700
Data Index: 4278162 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.6791. Min Act: -0.1700
Data Index: 1144172 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.7104. Min Act: -0.1700
Data Index: 1021384 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.7416. Min Act: -0.1700
Data Index: 6780172 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.6791. Min Act: -0.1700
Data Index: 5379397 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.6479. Min Act: -0.1700
Data Index: 8740332 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.6479. Min Act: -0.1700
Data Index: 2983525 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.6166. Min Act: -0.1700
Data Index: 3761626 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.5854. Min Act: -0.1700
Data Index: 2359033 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.6166. Min Act: -0.1700
Data Index: 8074345 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5229. Min Range: -6.5229
Max Act: 5.6166. Min Act: -0.1700
Data Index: 3237927 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19