Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1466 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.7777. Min Act: -0.1700
Data Index: 3524101 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.5589. Min Act: -0.1700
Data Index: 7431175 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.5589. Min Act: -0.1700
Data Index: 828542 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.5277. Min Act: -0.1700
Data Index: 6052639 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.4339. Min Act: -0.1700
Data Index: 6736555 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.3714. Min Act: -0.1700
Data Index: 1741086 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.3089. Min Act: -0.1700
Data Index: 1665181 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.3089. Min Act: -0.1700
Data Index: 1022587 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.3089. Min Act: -0.1700
Data Index: 2050006 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.2777. Min Act: -0.1700
Data Index: 4428386 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.3089. Min Act: -0.1700
Data Index: 5537771 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.2151. Min Act: -0.1700
Data Index: 2853832 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.2151. Min Act: -0.1700
Data Index: 7238347 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.2464. Min Act: -0.1700
Data Index: 758015 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.2464. Min Act: -0.1700
Data Index: 1524748 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.2464. Min Act: -0.1700
Data Index: 335653 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.2151. Min Act: -0.1700
Data Index: 6647770 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.2151. Min Act: -0.1700
Data Index: 4537207 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.2151. Min Act: -0.1700
Data Index: 6530596 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7777. Min Range: -4.7777
Max Act: 4.2151. Min Act: -0.1700
Data Index: 5998353 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19