Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3981 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.5323. Min Act: -0.1700
Data Index: 463163 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.3135. Min Act: -0.1700
Data Index: 7462781 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.2510. Min Act: -0.1700
Data Index: 8705309 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.2510. Min Act: -0.1700
Data Index: 1057476 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.2510. Min Act: -0.1700
Data Index: 682822 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.2510. Min Act: -0.1700
Data Index: 5879855 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.1260. Min Act: -0.1700
Data Index: 4050323 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.1260. Min Act: -0.1700
Data Index: 5065539 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.0948. Min Act: -0.1700
Data Index: 2004298 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.0948. Min Act: -0.1700
Data Index: 8409207 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.0635. Min Act: -0.1700
Data Index: 5575826 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.0635. Min Act: -0.1700
Data Index: 6806785 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.0635. Min Act: -0.1700
Data Index: 6914994 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.0635. Min Act: -0.1700
Data Index: 8032990 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.0323. Min Act: -0.1700
Data Index: 8803043 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.0010. Min Act: -0.1700
Data Index: 6410229 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.0323. Min Act: -0.1700
Data Index: 7169084 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5323. Min Range: -5.5323
Max Act: 5.0010. Min Act: -0.1700
Data Index: 8755213 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5323. Min Range: -5.5323
Max Act: 4.9698. Min Act: -0.1700
Data Index: 8072154 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5323. Min Range: -5.5323
Max Act: 4.9698. Min Act: -0.1700
Data Index: 1006208 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19