Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.8086. Min Act: -0.1700
Data Index: 5829101 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.7774. Min Act: -0.1700
Data Index: 2588221 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.6211. Min Act: -0.1700
Data Index: 3874446 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.5274. Min Act: -0.1700
Data Index: 8404070 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.4961. Min Act: -0.1700
Data Index: 8470482 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.4961. Min Act: -0.1700
Data Index: 1276420 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.4961. Min Act: -0.1700
Data Index: 5654707 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.4649. Min Act: -0.1700
Data Index: 7993810 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.4649. Min Act: -0.1700
Data Index: 5895976 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.4336. Min Act: -0.1700
Data Index: 7909689 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.4024. Min Act: -0.1700
Data Index: 6514080 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.3711. Min Act: -0.1700
Data Index: 4009383 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.3711. Min Act: -0.1700
Data Index: 3933736 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.3711. Min Act: -0.1700
Data Index: 3075591 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.3086. Min Act: -0.1700
Data Index: 4460853 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.2774. Min Act: -0.1700
Data Index: 3933739 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.2461. Min Act: -0.1700
Data Index: 5601045 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.2149. Min Act: -0.1700
Data Index: 5698312 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.2461. Min Act: -0.1700
Data Index: 5128 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8086. Min Range: -5.8086
Max Act: 5.2461. Min Act: -0.1700
Data Index: 1608138 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19