Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1309 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0757. Min Range: -7.0757
Max Act: 7.0757. Min Act: -0.1700
Data Index: 8260103 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.9507. Min Act: -0.1700
Data Index: 5989265 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.7632. Min Act: -0.1700
Data Index: 4187170 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.7319. Min Act: -0.1700
Data Index: 8706557 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.6694. Min Act: -0.1700
Data Index: 8448698 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.6382. Min Act: -0.1700
Data Index: 4118555 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.6382. Min Act: -0.1700
Data Index: 5868631 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.6069. Min Act: -0.1700
Data Index: 5900957 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.6069. Min Act: -0.1700
Data Index: 301112 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.5444. Min Act: -0.1700
Data Index: 8630930 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.5444. Min Act: -0.1700
Data Index: 3545442 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.5444. Min Act: -0.1700
Data Index: 2582617 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.5444. Min Act: -0.1700
Data Index: 1787309 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.5132. Min Act: -0.1700
Data Index: 7290384 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.5444. Min Act: -0.1700
Data Index: 1208959 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.5132. Min Act: -0.1700
Data Index: 2137912 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.4819. Min Act: -0.1700
Data Index: 2592660 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.4819. Min Act: -0.1700
Data Index: 157614 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.4819. Min Act: -0.1700
Data Index: 7973461 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0757. Min Range: -7.0757
Max Act: 6.4507. Min Act: -0.1700
Data Index: 7803103 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19