Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4556. Min Range: -6.4556
Max Act: 6.4556. Min Act: -0.1700
Data Index: 8308538 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4556. Min Range: -6.4556
Max Act: 6.3931. Min Act: -0.1700
Data Index: 8819786 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4556. Min Range: -6.4556
Max Act: 6.2681. Min Act: -0.1700
Data Index: 7712024 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4556. Min Range: -6.4556
Max Act: 6.2681. Min Act: -0.1700
Data Index: 3309896 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4556. Min Range: -6.4556
Max Act: 6.1743. Min Act: -0.1700
Data Index: 6200629 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4556. Min Range: -6.4556
Max Act: 6.1743. Min Act: -0.1700
Data Index: 757817 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4556. Min Range: -6.4556
Max Act: 6.1118. Min Act: -0.1700
Data Index: 8819783 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4556. Min Range: -6.4556
Max Act: 6.1118. Min Act: -0.1700
Data Index: 6609229 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4556. Min Range: -6.4556
Max Act: 6.1118. Min Act: -0.1700
Data Index: 757818 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4556. Min Range: -6.4556
Max Act: 6.0806. Min Act: -0.1700
Data Index: 2348504 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4556. Min Range: -6.4556
Max Act: 5.9868. Min Act: -0.1700
Data Index: 5524539 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4556. Min Range: -6.4556
Max Act: 5.9556. Min Act: -0.1700
Data Index: 4762438 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4556. Min Range: -6.4556
Max Act: 5.9556. Min Act: -0.1700
Data Index: 2557480 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4556. Min Range: -6.4556
Max Act: 5.9243. Min Act: -0.1700
Data Index: 7463258 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4556. Min Range: -6.4556
Max Act: 5.8931. Min Act: -0.1700
Data Index: 7364987 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4556. Min Range: -6.4556
Max Act: 5.8931. Min Act: -0.1700
Data Index: 3196098 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4556. Min Range: -6.4556
Max Act: 5.9243. Min Act: -0.1700
Data Index: 839498 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4556. Min Range: -6.4556
Max Act: 5.8931. Min Act: -0.1700
Data Index: 3054958 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4556. Min Range: -6.4556
Max Act: 5.8931. Min Act: -0.1700
Data Index: 8681173 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4556. Min Range: -6.4556
Max Act: 5.8306. Min Act: -0.1700
Data Index: 3902788 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19