Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1484 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3376. Min Range: -4.3376
Max Act: 4.3376. Min Act: -0.1700
Data Index: 1094221 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3376. Min Range: -4.3376
Max Act: 4.1188. Min Act: -0.1700
Data Index: 1959149 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3376. Min Range: -4.3376
Max Act: 4.0250. Min Act: -0.1700
Data Index: 8580336 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.9625. Min Act: -0.1700
Data Index: 4778784 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.9625. Min Act: -0.1700
Data Index: 1677545 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.9312. Min Act: -0.1700
Data Index: 605722 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.9312. Min Act: -0.1700
Data Index: 5868920 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.9312. Min Act: -0.1700
Data Index: 3402604 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.9000. Min Act: -0.1700
Data Index: 7832760 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.9000. Min Act: -0.1700
Data Index: 3033670 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.9312. Min Act: -0.1700
Data Index: 675427 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.8687. Min Act: -0.1700
Data Index: 7345674 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.8374. Min Act: -0.1700
Data Index: 8528464 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.8374. Min Act: -0.1700
Data Index: 2575472 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.8218. Min Act: -0.1700
Data Index: 6234693 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.8374. Min Act: -0.1700
Data Index: 5120587 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.8218. Min Act: -0.1700
Data Index: 7158899 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.8062. Min Act: -0.1700
Data Index: 8028983 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.7905. Min Act: -0.1700
Data Index: 4022273 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3376. Min Range: -4.3376
Max Act: 3.7749. Min Act: -0.1700
Data Index: 7775443 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19