Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1338 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.4841. Min Act: -0.1700
Data Index: 6446272 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2965. Min Act: -0.1700
Data Index: 7645315 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2653. Min Act: -0.1700
Data Index: 8529571 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2653. Min Act: -0.1700
Data Index: 7648043 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2653. Min Act: -0.1700
Data Index: 1179132 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2653. Min Act: -0.1700
Data Index: 3761054 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2653. Min Act: -0.1700
Data Index: 2544411 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2653. Min Act: -0.1700
Data Index: 7455315 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2028. Min Act: -0.1700
Data Index: 2813499 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2340. Min Act: -0.1700
Data Index: 247189 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2340. Min Act: -0.1700
Data Index: 1480468 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2028. Min Act: -0.1700
Data Index: 4302045 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2340. Min Act: -0.1700
Data Index: 1584876 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2340. Min Act: -0.1700
Data Index: 247191 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2653. Min Act: -0.1700
Data Index: 8174866 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2340. Min Act: -0.1700
Data Index: 8603100 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2028. Min Act: -0.1700
Data Index: 8209475 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2028. Min Act: -0.1700
Data Index: 263962 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.1715. Min Act: -0.1700
Data Index: 5361962 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4841. Min Range: -4.4841
Max Act: 4.2028. Min Act: -0.1700
Data Index: 3649063 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19