Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 894 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0372. Min Range: -5.0372
Max Act: 5.0372. Min Act: -0.1700
Data Index: 1331689 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.9747. Min Act: -0.1700
Data Index: 7500627 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.9122. Min Act: -0.1700
Data Index: 2776678 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.8185. Min Act: -0.1700
Data Index: 1823640 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.8185. Min Act: -0.1700
Data Index: 3829514 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.8185. Min Act: -0.1700
Data Index: 5061576 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.8185. Min Act: -0.1700
Data Index: 1745754 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.7872. Min Act: -0.1700
Data Index: 7012967 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.7560. Min Act: -0.1700
Data Index: 1360251 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.7560. Min Act: -0.1700
Data Index: 8455776 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.6622. Min Act: -0.1700
Data Index: 4419977 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.6622. Min Act: -0.1700
Data Index: 7012966 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.6310. Min Act: -0.1700
Data Index: 1845131 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.6622. Min Act: -0.1700
Data Index: 4273160 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.6622. Min Act: -0.1700
Data Index: 2456537 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.5997. Min Act: -0.1700
Data Index: 3431299 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.6310. Min Act: -0.1700
Data Index: 8597501 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.6310. Min Act: -0.1700
Data Index: 3030539 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.6310. Min Act: -0.1700
Data Index: 7902459 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0372. Min Range: -5.0372
Max Act: 4.5997. Min Act: -0.1700
Data Index: 4220232 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19