Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2150 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8323. Min Range: -8.8323
Max Act: 8.8323. Min Act: -0.1700
Data Index: 5457729 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.8323. Min Act: -0.1700
Data Index: 3918376 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.8323. Min Act: -0.1700
Data Index: 1982010 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.7698. Min Act: -0.1700
Data Index: 4199994 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.7698. Min Act: -0.1700
Data Index: 2252611 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.6448. Min Act: -0.1700
Data Index: 1129602 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.5198. Min Act: -0.1700
Data Index: 7579015 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.5823. Min Act: -0.1700
Data Index: 2744220 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.4573. Min Act: -0.1700
Data Index: 2239937 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.4573. Min Act: -0.1700
Data Index: 789641 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.3635. Min Act: -0.1700
Data Index: 7820805 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.3635. Min Act: -0.1700
Data Index: 4836869 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.3323. Min Act: -0.1700
Data Index: 789046 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.3323. Min Act: -0.1700
Data Index: 3019778 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.3010. Min Act: -0.1700
Data Index: 2518424 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.3010. Min Act: -0.1700
Data Index: 5305443 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.3010. Min Act: -0.1700
Data Index: 3091501 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.2698. Min Act: -0.1700
Data Index: 5054886 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.2385. Min Act: -0.1700
Data Index: 3499682 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8323. Min Range: -8.8323
Max Act: 7.2698. Min Act: -0.1700
Data Index: 1102768 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19