Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2641 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6616. Min Range: -8.6616
Max Act: 8.6616. Min Act: -0.1700
Data Index: 7405331 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6616. Min Range: -8.6616
Max Act: 8.4116. Min Act: -0.1700
Data Index: 1712425 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6616. Min Range: -8.6616
Max Act: 8.0991. Min Act: -0.1700
Data Index: 2487741 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6616. Min Range: -8.6616
Max Act: 8.0366. Min Act: -0.1700
Data Index: 2409292 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.9741. Min Act: -0.1700
Data Index: 3917039 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.9116. Min Act: -0.1700
Data Index: 3958660 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.9116. Min Act: -0.1700
Data Index: 3951000 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.9116. Min Act: -0.1700
Data Index: 8246321 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.9116. Min Act: -0.1700
Data Index: 5056407 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.8178. Min Act: -0.1700
Data Index: 5121417 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.7866. Min Act: -0.1700
Data Index: 4525302 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.7553. Min Act: -0.1700
Data Index: 1471374 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.7553. Min Act: -0.1700
Data Index: 3767660 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.7553. Min Act: -0.1700
Data Index: 5251839 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.7553. Min Act: -0.1700
Data Index: 2503291 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.7241. Min Act: -0.1700
Data Index: 8446417 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.6928. Min Act: -0.1700
Data Index: 212489 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.6928. Min Act: -0.1700
Data Index: 8246315 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.6616. Min Act: -0.1700
Data Index: 6686171 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6616. Min Range: -8.6616
Max Act: 7.6616. Min Act: -0.1700
Data Index: 2491565 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19