Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3229. Min Range: -12.3229
Max Act: 12.3229. Min Act: -0.1700
Data Index: 2655620 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3229. Min Range: -12.3229
Max Act: 12.0729. Min Act: -0.1700
Data Index: 5318574 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.5104. Min Act: -0.1700
Data Index: 1926052 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.3229. Min Act: -0.1700
Data Index: 4321634 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.2604. Min Act: -0.1700
Data Index: 7977736 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.1979. Min Act: -0.1700
Data Index: 5324889 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.1354. Min Act: -0.1700
Data Index: 3612874 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.1354. Min Act: -0.1700
Data Index: 8537852 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.0729. Min Act: -0.1700
Data Index: 2489185 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.0729. Min Act: -0.1700
Data Index: 2150055 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.0104. Min Act: -0.1700
Data Index: 7743548 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.0729. Min Act: -0.1699
Data Index: 1257980 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.0729. Min Act: -0.1700
Data Index: 6247904 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.0729. Min Act: -0.1700
Data Index: 5612738 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3229. Min Range: -12.3229
Max Act: 11.0104. Min Act: -0.1700
Data Index: 6566659 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3229. Min Range: -12.3229
Max Act: 10.9479. Min Act: -0.1700
Data Index: 6511113 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3229. Min Range: -12.3229
Max Act: 10.9479. Min Act: -0.1700
Data Index: 2308661 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3229. Min Range: -12.3229
Max Act: 10.8854. Min Act: -0.1700
Data Index: 1645682 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3229. Min Range: -12.3229
Max Act: 10.8854. Min Act: -0.1700
Data Index: 2638341 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3229. Min Range: -12.3229
Max Act: 10.8854. Min Act: -0.1700
Data Index: 3571058 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19