Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.6351. Min Act: -0.1700
Data Index: 484753 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.6039. Min Act: -0.1700
Data Index: 2651817 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.4789. Min Act: -0.1700
Data Index: 7961364 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.4789. Min Act: -0.1700
Data Index: 57993 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.3539. Min Act: -0.1700
Data Index: 1923750 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.3226. Min Act: -0.1700
Data Index: 4092308 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.2914. Min Act: -0.1700
Data Index: 1923751 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.2914. Min Act: -0.1700
Data Index: 1257942 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.1664. Min Act: -0.1700
Data Index: 1182966 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.1351. Min Act: -0.1700
Data Index: 5744410 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.1351. Min Act: -0.1700
Data Index: 7448367 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.1664. Min Act: -0.1700
Data Index: 2513393 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.1039. Min Act: -0.1700
Data Index: 2248479 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.0726. Min Act: -0.1700
Data Index: 7692852 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.1039. Min Act: -0.1700
Data Index: 1520977 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.0726. Min Act: -0.1700
Data Index: 468201 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.0726. Min Act: -0.1700
Data Index: 6215931 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.0414. Min Act: -0.1700
Data Index: 33680 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.0414. Min Act: -0.1700
Data Index: 1893569 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6351. Min Range: -6.6351
Max Act: 6.0414. Min Act: -0.1700
Data Index: 1380199 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19