Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6645. Min Range: -7.6645
Max Act: 7.6645. Min Act: -0.1700
Data Index: 6378695 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6645. Min Range: -7.6645
Max Act: 7.2895. Min Act: -0.1700
Data Index: 2070012 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6645. Min Range: -7.6645
Max Act: 7.2270. Min Act: -0.1700
Data Index: 8507992 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6645. Min Range: -7.6645
Max Act: 7.1020. Min Act: -0.1700
Data Index: 6456175 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6645. Min Range: -7.6645
Max Act: 7.1332. Min Act: -0.1700
Data Index: 3356114 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6645. Min Range: -7.6645
Max Act: 7.1020. Min Act: -0.1700
Data Index: 810749 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6645. Min Range: -7.6645
Max Act: 7.0707. Min Act: -0.1700
Data Index: 399911 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6645. Min Range: -7.6645
Max Act: 7.0395. Min Act: -0.1700
Data Index: 2621092 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6645. Min Range: -7.6645
Max Act: 7.0395. Min Act: -0.1700
Data Index: 2070013 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.9770. Min Act: -0.1700
Data Index: 6220683 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.9457. Min Act: -0.1700
Data Index: 5967774 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.9145. Min Act: -0.1700
Data Index: 7166741 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.9145. Min Act: -0.1700
Data Index: 1688268 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.9145. Min Act: -0.1700
Data Index: 2890291 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.8832. Min Act: -0.1700
Data Index: 3118112 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.9145. Min Act: -0.1700
Data Index: 1324364 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.8520. Min Act: -0.1700
Data Index: 4831830 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.8207. Min Act: -0.1700
Data Index: 4962459 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.8207. Min Act: -0.1700
Data Index: 7729506 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6645. Min Range: -7.6645
Max Act: 6.8207. Min Act: -0.1700
Data Index: 5920067 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19