Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 620 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.2063. Min Range: -15.2063
Max Act: 15.2063. Min Act: -0.1700
Data Index: 740276 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.9563. Min Act: -0.1700
Data Index: 3077715 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.9563. Min Act: -0.1700
Data Index: 8489337 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.9563. Min Act: -0.1700
Data Index: 4292523 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.9563. Min Act: -0.1700
Data Index: 5930962 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.8938. Min Act: -0.1700
Data Index: 274773 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.8938. Min Act: -0.1700
Data Index: 5576296 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.8313. Min Act: -0.1700
Data Index: 347752 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.8938. Min Act: -0.1700
Data Index: 2432371 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.8313. Min Act: -0.1700
Data Index: 7790978 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.8313. Min Act: -0.1700
Data Index: 8704211 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.7688. Min Act: -0.1700
Data Index: 2398364 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.7688. Min Act: -0.1700
Data Index: 986969 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.7688. Min Act: -0.1700
Data Index: 7122573 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.7688. Min Act: -0.1700
Data Index: 4513749 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.7063. Min Act: -0.1700
Data Index: 6910024 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.7063. Min Act: -0.1700
Data Index: 6132078 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.7063. Min Act: -0.1700
Data Index: 7207143 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.7063. Min Act: -0.1700
Data Index: 1342800 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.2063. Min Range: -15.2063
Max Act: 14.7688. Min Act: -0.1700
Data Index: 6258929 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19