Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 285 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5613. Min Range: -8.5613
Max Act: 8.5613. Min Act: -0.1700
Data Index: 2272856 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5613. Min Range: -8.5613
Max Act: 8.1238. Min Act: -0.1700
Data Index: 4963421 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.9988. Min Act: -0.1700
Data Index: 6640712 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.9363. Min Act: -0.1700
Data Index: 5885587 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.9363. Min Act: -0.1700
Data Index: 897589 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.8738. Min Act: -0.1700
Data Index: 6822814 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.8738. Min Act: -0.1700
Data Index: 2004144 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.8738. Min Act: -0.1700
Data Index: 619330 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.8113. Min Act: -0.1700
Data Index: 8034282 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.8113. Min Act: -0.1700
Data Index: 7627905 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.7488. Min Act: -0.1700
Data Index: 4247522 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.7175. Min Act: -0.1700
Data Index: 207634 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.7175. Min Act: -0.1700
Data Index: 2766458 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.6863. Min Act: -0.1700
Data Index: 4331431 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.6550. Min Act: -0.1700
Data Index: 6702768 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.6238. Min Act: -0.1700
Data Index: 7389544 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.6238. Min Act: -0.1700
Data Index: 7890868 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.5925. Min Act: -0.1700
Data Index: 4643370 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.5613. Min Act: -0.1700
Data Index: 988985 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5613. Min Range: -8.5613
Max Act: 7.5613. Min Act: -0.1700
Data Index: 3255417 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19