Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 632 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2227. Min Range: -6.2227
Max Act: 6.2227. Min Act: -0.1700
Data Index: 1994253 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2227. Min Range: -6.2227
Max Act: 6.0977. Min Act: -0.1700
Data Index: 5025938 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2227. Min Range: -6.2227
Max Act: 6.0977. Min Act: -0.1700
Data Index: 1090780 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2227. Min Range: -6.2227
Max Act: 6.0977. Min Act: -0.1700
Data Index: 8260114 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2227. Min Range: -6.2227
Max Act: 6.0352. Min Act: -0.1700
Data Index: 246896 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.9727. Min Act: -0.1700
Data Index: 2387044 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8790. Min Act: -0.1700
Data Index: 2163660 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.9102. Min Act: -0.1700
Data Index: 4999894 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8790. Min Act: -0.1700
Data Index: 6531611 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8165. Min Act: -0.1700
Data Index: 7189337 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8165. Min Act: -0.1700
Data Index: 6822561 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8165. Min Act: -0.1700
Data Index: 7407712 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8477. Min Act: -0.1700
Data Index: 3236023 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7540. Min Act: -0.1700
Data Index: 3481554 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7540. Min Act: -0.1700
Data Index: 7166 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7227. Min Act: -0.1700
Data Index: 1240335 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7227. Min Act: -0.1700
Data Index: 213144 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7227. Min Act: -0.1700
Data Index: 8810362 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7227. Min Act: -0.1700
Data Index: 8797109 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7227. Min Act: -0.1700
Data Index: 5851103 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19