Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.8227. Min Act: -0.1700
Data Index: 4739608 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.7915. Min Act: -0.1700
Data Index: 1263903 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.7602. Min Act: -0.1700
Data Index: 3293605 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.7290. Min Act: -0.1700
Data Index: 656769 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.7290. Min Act: -0.1700
Data Index: 4699336 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.7602. Min Act: -0.1700
Data Index: 7194913 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.6352. Min Act: -0.1700
Data Index: 818363 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.5727. Min Act: -0.1700
Data Index: 3344951 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.5727. Min Act: -0.1700
Data Index: 7432604 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.5727. Min Act: -0.1700
Data Index: 7616583 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.5415. Min Act: -0.1700
Data Index: 4374783 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.5102. Min Act: -0.1700
Data Index: 1055832 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.5727. Min Act: -0.1700
Data Index: 602456 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.5102. Min Act: -0.1700
Data Index: 7770521 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.5415. Min Act: -0.1700
Data Index: 7823338 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.5102. Min Act: -0.1700
Data Index: 4561762 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.5102. Min Act: -0.1700
Data Index: 8200984 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.4790. Min Act: -0.1700
Data Index: 3319255 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.4790. Min Act: -0.1700
Data Index: 5551568 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8227. Min Range: -6.8227
Max Act: 6.4790. Min Act: -0.1700
Data Index: 367339 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19