Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2137 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4173. Min Range: -8.4173
Max Act: 8.4173. Min Act: -0.1700
Data Index: 2204183 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4173. Min Range: -8.4173
Max Act: 8.4173. Min Act: -0.1700
Data Index: 3903389 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4173. Min Range: -8.4173
Max Act: 8.1673. Min Act: -0.1700
Data Index: 1602346 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.9798. Min Act: -0.1700
Data Index: 1326341 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.9173. Min Act: -0.1700
Data Index: 5689196 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.9173. Min Act: -0.1700
Data Index: 3496727 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.9173. Min Act: -0.1700
Data Index: 1326340 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.9173. Min Act: -0.1700
Data Index: 6508987 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.8548. Min Act: -0.1700
Data Index: 4918423 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.8548. Min Act: -0.1700
Data Index: 8234631 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.8548. Min Act: -0.1700
Data Index: 1326343 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.7923. Min Act: -0.1700
Data Index: 586437 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.7298. Min Act: -0.1700
Data Index: 806148 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.7298. Min Act: -0.1700
Data Index: 8150846 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.6986. Min Act: -0.1700
Data Index: 4694089 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.7298. Min Act: -0.1700
Data Index: 2731861 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.7298. Min Act: -0.1700
Data Index: 1611099 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.6986. Min Act: -0.1700
Data Index: 6218730 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.6986. Min Act: -0.1700
Data Index: 1417179 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4173. Min Range: -8.4173
Max Act: 7.6673. Min Act: -0.1700
Data Index: 4573050 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19