Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3727 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.9435. Min Act: -0.1700
Data Index: 4288272 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.9122. Min Act: -0.1700
Data Index: 1775639 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.8810. Min Act: -0.1700
Data Index: 6230545 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.8185. Min Act: -0.1700
Data Index: 1323328 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7872. Min Act: -0.1700
Data Index: 4910361 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7872. Min Act: -0.1700
Data Index: 1751740 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7560. Min Act: -0.1700
Data Index: 1262604 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7560. Min Act: -0.1700
Data Index: 8571529 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7560. Min Act: -0.1700
Data Index: 4755456 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7560. Min Act: -0.1700
Data Index: 6777269 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7247. Min Act: -0.1700
Data Index: 7269914 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7247. Min Act: -0.1700
Data Index: 246218 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7247. Min Act: -0.1700
Data Index: 7357937 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7247. Min Act: -0.1700
Data Index: 6885406 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7247. Min Act: -0.1700
Data Index: 3350263 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7247. Min Act: -0.1700
Data Index: 4238936 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7247. Min Act: -0.1700
Data Index: 1543254 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.6935. Min Act: -0.1700
Data Index: 1609397 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.7247. Min Act: -0.1700
Data Index: 4338452 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9435. Min Range: -5.9435
Max Act: 5.6935. Min Act: -0.1700
Data Index: 6328045 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19