Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4868 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9944. Min Range: -9.9944
Max Act: 9.9944. Min Act: -0.1700
Data Index: 5937447 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9944. Min Range: -9.9944
Max Act: 9.1819. Min Act: -0.1700
Data Index: 7798045 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.9319. Min Act: -0.1700
Data Index: 1898757 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.9319. Min Act: -0.1700
Data Index: 1748895 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.8069. Min Act: -0.1699
Data Index: 676147 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.6194. Min Act: -0.1700
Data Index: 4784617 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.6819. Min Act: -0.1700
Data Index: 4915969 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.6194. Min Act: -0.1700
Data Index: 7704983 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.5569. Min Act: -0.1700
Data Index: 1771385 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.5569. Min Act: -0.1700
Data Index: 2765504 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.5569. Min Act: -0.1700
Data Index: 631660 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.4944. Min Act: -0.1699
Data Index: 3757643 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.4944. Min Act: -0.1700
Data Index: 7179588 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.4319. Min Act: -0.1700
Data Index: 532170 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.4319. Min Act: -0.1700
Data Index: 4476524 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.4319. Min Act: -0.1700
Data Index: 6088049 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.4944. Min Act: -0.1700
Data Index: 6425270 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.4944. Min Act: -0.1700
Data Index: 8690529 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.3694. Min Act: -0.1700
Data Index: 7036297 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9944. Min Range: -9.9944
Max Act: 8.3694. Min Act: -0.1700
Data Index: 7101273 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19