Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 371 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.6913. Min Act: -0.1700
Data Index: 371772 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.4413. Min Act: -0.1700
Data Index: 8519772 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.2851. Min Act: -0.1700
Data Index: 3930159 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.2538. Min Act: -0.1700
Data Index: 493440 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.2538. Min Act: -0.1700
Data Index: 3054907 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.2226. Min Act: -0.1700
Data Index: 2058366 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.2538. Min Act: -0.1700
Data Index: 5745708 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.1601. Min Act: -0.1700
Data Index: 4274458 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.1601. Min Act: -0.1700
Data Index: 2529675 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.0351. Min Act: -0.1700
Data Index: 5162782 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.0351. Min Act: -0.1700
Data Index: 7854067 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6913. Min Range: -7.6913
Max Act: 7.0351. Min Act: -0.1700
Data Index: 1885667 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6913. Min Range: -7.6913
Max Act: 6.9726. Min Act: -0.1700
Data Index: 5019485 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6913. Min Range: -7.6913
Max Act: 6.9726. Min Act: -0.1700
Data Index: 5431761 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6913. Min Range: -7.6913
Max Act: 6.9726. Min Act: -0.1700
Data Index: 5312864 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6913. Min Range: -7.6913
Max Act: 6.9726. Min Act: -0.1700
Data Index: 2149542 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6913. Min Range: -7.6913
Max Act: 6.9413. Min Act: -0.1700
Data Index: 8646397 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6913. Min Range: -7.6913
Max Act: 6.9101. Min Act: -0.1700
Data Index: 7475908 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6913. Min Range: -7.6913
Max Act: 6.9101. Min Act: -0.1700
Data Index: 1097042 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6913. Min Range: -7.6913
Max Act: 6.9101. Min Act: -0.1700
Data Index: 639696 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19