Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0434. Min Range: -4.0434
Max Act: 4.0434. Min Act: -0.1700
Data Index: 667032 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.9183. Min Act: -0.1700
Data Index: 350251 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.8871. Min Act: -0.1700
Data Index: 3729438 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.8558. Min Act: -0.1700
Data Index: 978203 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.7620. Min Act: -0.1700
Data Index: 5784947 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.7620. Min Act: -0.1700
Data Index: 4479755 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.7307. Min Act: -0.1700
Data Index: 2362268 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.7307. Min Act: -0.1700
Data Index: 2105497 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.7307. Min Act: -0.1700
Data Index: 4834751 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.6681. Min Act: -0.1700
Data Index: 4014924 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.6681. Min Act: -0.1700
Data Index: 3439455 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.6368. Min Act: -0.1700
Data Index: 4783014 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.6368. Min Act: -0.1700
Data Index: 2362265 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.6368. Min Act: -0.1700
Data Index: 377042 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.6055. Min Act: -0.1700
Data Index: 577056 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.6055. Min Act: -0.1700
Data Index: 2303963 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.6055. Min Act: -0.1700
Data Index: 1129115 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.6055. Min Act: -0.1700
Data Index: 1499474 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.6055. Min Act: -0.1700
Data Index: 6324779 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0434. Min Range: -4.0434
Max Act: 3.5899. Min Act: -0.1700
Data Index: 3280863 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19