Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6372 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.9723. Min Act: -0.1700
Data Index: 3878469 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.9213. Min Act: -0.1687
Data Index: 6766102 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.9043. Min Act: -0.1700
Data Index: 5839440 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8872. Min Act: -0.1700
Data Index: 1821560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8872. Min Act: -0.1621
Data Index: 3895284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8701. Min Act: -0.1642
Data Index: 3812617 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8701. Min Act: -0.1700
Data Index: 3655252 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8701. Min Act: -0.1697
Data Index: 1190983 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8359. Min Act: -0.1700
Data Index: 1440681 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8701. Min Act: -0.1700
Data Index: 3083409 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8530. Min Act: -0.1700
Data Index: 4243747 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8359. Min Act: -0.1700
Data Index: 2099157 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8359. Min Act: -0.1688
Data Index: 6002788 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8187. Min Act: -0.1575
Data Index: 3551449 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8015. Min Act: -0.1696
Data Index: 7431103 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.7929. Min Act: -0.1700
Data Index: 127899 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.8015. Min Act: -0.1700
Data Index: 6940568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.7929. Min Act: -0.1700
Data Index: 4808900 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.7757. Min Act: -0.1697
Data Index: 371979 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9723. Min Range: -1.9723
Max Act: 1.7757. Min Act: -0.1700
Data Index: 5154983 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19