Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.9996. Min Act: -0.1700
Data Index: 2962969 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.5621. Min Act: -0.1700
Data Index: 2987429 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.4996. Min Act: -0.1700
Data Index: 381045 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.3746. Min Act: -0.1700
Data Index: 7623121 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.3746. Min Act: -0.1700
Data Index: 4269829 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.3121. Min Act: -0.1700
Data Index: 5796055 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.2496. Min Act: -0.1700
Data Index: 4074802 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.1871. Min Act: -0.1700
Data Index: 8499424 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.2496. Min Act: -0.1700
Data Index: 7746744 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.1246. Min Act: -0.1700
Data Index: 8667187 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.1558. Min Act: -0.1700
Data Index: 4274829 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.1246. Min Act: -0.1700
Data Index: 1177435 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.0933. Min Act: -0.1700
Data Index: 966395 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.0933. Min Act: -0.1700
Data Index: 7131094 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.0308. Min Act: -0.1700
Data Index: 2824706 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.0308. Min Act: -0.1700
Data Index: 1671705 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.0308. Min Act: -0.1700
Data Index: 1101633 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9996. Min Range: -8.9996
Max Act: 8.0308. Min Act: -0.1700
Data Index: 2330206 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9996. Min Range: -8.9996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 7824689 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9996. Min Range: -8.9996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 7649250 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19