Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.5297. Min Act: -0.1700
Data Index: 5275044 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.4672. Min Act: -0.1700
Data Index: 4566915 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.4359. Min Act: -0.1700
Data Index: 3703188 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.4359. Min Act: -0.1700
Data Index: 7714131 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.4047. Min Act: -0.1700
Data Index: 3693751 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.3109. Min Act: -0.1700
Data Index: 1452780 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.3109. Min Act: -0.1700
Data Index: 1702385 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.2797. Min Act: -0.1700
Data Index: 1718988 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.1547. Min Act: -0.1700
Data Index: 3577256 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.1234. Min Act: -0.1700
Data Index: 1501179 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.1234. Min Act: -0.1700
Data Index: 5593919 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.1234. Min Act: -0.1700
Data Index: 426042 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.1234. Min Act: -0.1700
Data Index: 6127097 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.0922. Min Act: -0.1700
Data Index: 7437513 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.0609. Min Act: -0.1700
Data Index: 7340600 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.0609. Min Act: -0.1700
Data Index: 3957078 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.0609. Min Act: -0.1700
Data Index: 5851234 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.0609. Min Act: -0.1700
Data Index: 3588105 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.0609. Min Act: -0.1700
Data Index: 4989170 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5297. Min Range: -7.5297
Max Act: 7.0297. Min Act: -0.1700
Data Index: 6085832 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19