Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1071 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0351. Min Range: -5.0351
Max Act: 5.0351. Min Act: -0.1700
Data Index: 6135463 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.9726. Min Act: -0.1700
Data Index: 8356219 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.9726. Min Act: -0.1700
Data Index: 6757174 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.9414. Min Act: -0.1700
Data Index: 1346807 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.8789. Min Act: -0.1700
Data Index: 8108164 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.8476. Min Act: -0.1700
Data Index: 2289976 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7226. Min Act: -0.1700
Data Index: 6939909 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6914. Min Act: -0.1700
Data Index: 8453598 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6601. Min Act: -0.1700
Data Index: 7019100 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6601. Min Act: -0.1700
Data Index: 1313202 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6289. Min Act: -0.1700
Data Index: 352251 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.5976. Min Act: -0.1700
Data Index: 5160619 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6601. Min Act: -0.1700
Data Index: 7502769 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.5976. Min Act: -0.1700
Data Index: 3373961 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.5976. Min Act: -0.1700
Data Index: 1770984 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.5976. Min Act: -0.1700
Data Index: 6792423 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.5976. Min Act: -0.1700
Data Index: 4554052 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.5664. Min Act: -0.1700
Data Index: 7488617 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.5976. Min Act: -0.1700
Data Index: 3545356 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.5664. Min Act: -0.1700
Data Index: 5693779 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19