Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6821. Min Range: -6.6821
Max Act: 6.6821. Min Act: -0.1700
Data Index: 1784082 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6821. Min Range: -6.6821
Max Act: 6.4633. Min Act: -0.1700
Data Index: 3129627 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.9633. Min Act: -0.1700
Data Index: 6069428 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.8696. Min Act: -0.1700
Data Index: 8364434 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.8696. Min Act: -0.1700
Data Index: 3671959 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.8383. Min Act: -0.1700
Data Index: 6685450 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.8383. Min Act: -0.1700
Data Index: 3581744 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.8383. Min Act: -0.1700
Data Index: 4800917 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.7758. Min Act: -0.1700
Data Index: 446200 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.7446. Min Act: -0.1700
Data Index: 7254538 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.7446. Min Act: -0.1700
Data Index: 7807307 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.7133. Min Act: -0.1700
Data Index: 6602329 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.6821. Min Act: -0.1700
Data Index: 978514 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.6821. Min Act: -0.1700
Data Index: 1878966 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.6508. Min Act: -0.1700
Data Index: 3133527 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.6508. Min Act: -0.1700
Data Index: 587851 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.6508. Min Act: -0.1700
Data Index: 4322177 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.6196. Min Act: -0.1700
Data Index: 2513669 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.5883. Min Act: -0.1700
Data Index: 4905675 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6821. Min Range: -6.6821
Max Act: 5.5883. Min Act: -0.1700
Data Index: 1543630 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19