Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3936. Min Range: -8.3936
Max Act: 8.3936. Min Act: -0.1700
Data Index: 3092995 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3936. Min Range: -8.3936
Max Act: 8.1749. Min Act: -0.1700
Data Index: 7193574 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3936. Min Range: -8.3936
Max Act: 8.1436. Min Act: -0.1700
Data Index: 147410 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3936. Min Range: -8.3936
Max Act: 8.1436. Min Act: -0.1700
Data Index: 6480756 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.9249. Min Act: -0.1700
Data Index: 2181981 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.8936. Min Act: -0.1700
Data Index: 1288209 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.8311. Min Act: -0.1700
Data Index: 6070031 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.7686. Min Act: -0.1700
Data Index: 6423213 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.7686. Min Act: -0.1700
Data Index: 7397121 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.7374. Min Act: -0.1700
Data Index: 4975866 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.7374. Min Act: -0.1700
Data Index: 8804553 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.7061. Min Act: -0.1700
Data Index: 6340228 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.7061. Min Act: -0.1700
Data Index: 7487181 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.6436. Min Act: -0.1700
Data Index: 2619296 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.6749. Min Act: -0.1700
Data Index: 1345007 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.6124. Min Act: -0.1700
Data Index: 4279 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.6124. Min Act: -0.1700
Data Index: 7849321 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.5811. Min Act: -0.1700
Data Index: 7294817 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.5811. Min Act: -0.1700
Data Index: 8150661 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3936. Min Range: -8.3936
Max Act: 7.5499. Min Act: -0.1700
Data Index: 878618 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19