Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2464 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7191. Min Range: -8.7191
Max Act: 8.7191. Min Act: -0.1700
Data Index: 5374438 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7191. Min Range: -8.7191
Max Act: 8.1254. Min Act: -0.1700
Data Index: 5374440 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7191. Min Range: -8.7191
Max Act: 8.1254. Min Act: -0.1700
Data Index: 3293829 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7191. Min Range: -8.7191
Max Act: 8.0004. Min Act: -0.1700
Data Index: 768481 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7191. Min Range: -8.7191
Max Act: 8.0004. Min Act: -0.1700
Data Index: 6197132 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7191. Min Range: -8.7191
Max Act: 8.0004. Min Act: -0.1700
Data Index: 7916691 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.9379. Min Act: -0.1700
Data Index: 1034359 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.8754. Min Act: -0.1700
Data Index: 3341962 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.9066. Min Act: -0.1700
Data Index: 3493678 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.8129. Min Act: -0.1700
Data Index: 4288454 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.7816. Min Act: -0.1700
Data Index: 532536 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.8441. Min Act: -0.1700
Data Index: 5521352 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.6879. Min Act: -0.1700
Data Index: 3309357 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.6566. Min Act: -0.1700
Data Index: 3262345 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.6566. Min Act: -0.1700
Data Index: 7323681 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.6566. Min Act: -0.1700
Data Index: 1161698 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.6879. Min Act: -0.1700
Data Index: 1780714 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.6254. Min Act: -0.1700
Data Index: 2397624 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.5941. Min Act: -0.1700
Data Index: 1594976 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7191. Min Range: -8.7191
Max Act: 7.5941. Min Act: -0.1700
Data Index: 644631 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19