Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6051 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4306. Min Range: -8.4306
Max Act: 8.4306. Min Act: -0.1700
Data Index: 3772732 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4306. Min Range: -8.4306
Max Act: 8.3681. Min Act: -0.1700
Data Index: 7604260 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4306. Min Range: -8.4306
Max Act: 8.3056. Min Act: -0.1700
Data Index: 3772730 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4306. Min Range: -8.4306
Max Act: 8.1181. Min Act: -0.1700
Data Index: 7110064 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4306. Min Range: -8.4306
Max Act: 8.0556. Min Act: -0.1700
Data Index: 8267204 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.9931. Min Act: -0.1699
Data Index: 7925854 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.9931. Min Act: -0.1700
Data Index: 5580263 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.9306. Min Act: -0.1700
Data Index: 600691 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.8994. Min Act: -0.1700
Data Index: 5712021 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.8994. Min Act: -0.1700
Data Index: 6792145 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.8681. Min Act: -0.1700
Data Index: 287173 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.7431. Min Act: -0.1700
Data Index: 5868041 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.7431. Min Act: -0.1700
Data Index: 4569977 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.7431. Min Act: -0.1700
Data Index: 4534261 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.7119. Min Act: -0.1700
Data Index: 5881784 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.7744. Min Act: -0.1700
Data Index: 6238015 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.7119. Min Act: -0.1700
Data Index: 6061097 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.6806. Min Act: -0.1700
Data Index: 5162509 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.6806. Min Act: -0.1700
Data Index: 8118183 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4306. Min Range: -8.4306
Max Act: 7.6181. Min Act: -0.1700
Data Index: 7925853 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19