Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.4065. Min Act: -0.1700
Data Index: 5658681 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.3752. Min Act: -0.1700
Data Index: 4229580 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.3752. Min Act: -0.1700
Data Index: 1417339 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.3127. Min Act: -0.1700
Data Index: 8788684 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.3127. Min Act: -0.1700
Data Index: 4168147 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.3127. Min Act: -0.1700
Data Index: 3641354 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.2815. Min Act: -0.1700
Data Index: 2200959 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.2815. Min Act: -0.1700
Data Index: 4168141 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.2502. Min Act: -0.1698
Data Index: 2773344 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.2502. Min Act: -0.1700
Data Index: 7828387 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.2502. Min Act: -0.1700
Data Index: 6226209 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.2502. Min Act: -0.1700
Data Index: 4191078 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.2502. Min Act: -0.1700
Data Index: 6707907 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.2502. Min Act: -0.1700
Data Index: 5690879 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.2190. Min Act: -0.1700
Data Index: 8730578 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.2190. Min Act: -0.1700
Data Index: 8531870 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.1877. Min Act: -0.1698
Data Index: 2011781 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.1877. Min Act: -0.1700
Data Index: 3720330 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.1877. Min Act: -0.1700
Data Index: 5186016 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4065. Min Range: -5.4065
Max Act: 5.1877. Min Act: -0.1700
Data Index: 6807421 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19