Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2429. Min Range: -6.2429
Max Act: 6.2429. Min Act: -0.1700
Data Index: 7492285 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2429. Min Range: -6.2429
Max Act: 6.1804. Min Act: -0.1700
Data Index: 3707507 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.9929. Min Act: -0.1700
Data Index: 4926932 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.9617. Min Act: -0.1700
Data Index: 1838618 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.8992. Min Act: -0.1700
Data Index: 4179930 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.8054. Min Act: -0.1700
Data Index: 6293354 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.8679. Min Act: -0.1700
Data Index: 5366894 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.8367. Min Act: -0.1700
Data Index: 5480695 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.8367. Min Act: -0.1700
Data Index: 2854778 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.7742. Min Act: -0.1700
Data Index: 2855818 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.7429. Min Act: -0.1700
Data Index: 521961 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.7117. Min Act: -0.1700
Data Index: 5877021 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.7117. Min Act: -0.1700
Data Index: 3809584 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.7117. Min Act: -0.1700
Data Index: 1557486 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.7117. Min Act: -0.1700
Data Index: 5514970 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.6804. Min Act: -0.1700
Data Index: 8246603 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.6804. Min Act: -0.1700
Data Index: 2541994 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.6492. Min Act: -0.1700
Data Index: 1687478 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.6492. Min Act: -0.1700
Data Index: 6451635 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2429. Min Range: -6.2429
Max Act: 5.6804. Min Act: -0.1700
Data Index: 747163 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19