Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6325 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.8616. Min Act: -0.1700
Data Index: 222350 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.7054. Min Act: -0.1700
Data Index: 4964461 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.5804. Min Act: -0.1700
Data Index: 3225104 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.4866. Min Act: -0.1700
Data Index: 1015360 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.4554. Min Act: -0.1700
Data Index: 6321450 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.4241. Min Act: -0.1700
Data Index: 1235995 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.3929. Min Act: -0.1700
Data Index: 7323069 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.3616. Min Act: -0.1700
Data Index: 4806262 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.3304. Min Act: -0.1700
Data Index: 1709738 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.3304. Min Act: -0.1700
Data Index: 8732844 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.2679. Min Act: -0.1700
Data Index: 6966843 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.2054. Min Act: -0.1700
Data Index: 6791076 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.2054. Min Act: -0.1700
Data Index: 300058 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.2054. Min Act: -0.1700
Data Index: 1033468 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.2054. Min Act: -0.1700
Data Index: 714584 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.2054. Min Act: -0.1700
Data Index: 1080562 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.1429. Min Act: -0.1700
Data Index: 8395879 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.1429. Min Act: -0.1700
Data Index: 747673 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.1116. Min Act: -0.1700
Data Index: 3493478 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8616. Min Range: -5.8616
Max Act: 5.1116. Min Act: -0.1700
Data Index: 2577599 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19