Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4103 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.8806. Min Act: -0.1700
Data Index: 808398 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.8181. Min Act: -0.1700
Data Index: 3598955 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.8493. Min Act: -0.1700
Data Index: 6379486 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.7556. Min Act: -0.1700
Data Index: 4220968 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.7556. Min Act: -0.1700
Data Index: 2364304 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.7243. Min Act: -0.1700
Data Index: 7628075 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.7243. Min Act: -0.1700
Data Index: 3966471 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.6618. Min Act: -0.1700
Data Index: 8571369 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.6618. Min Act: -0.1700
Data Index: 1245796 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.6618. Min Act: -0.1700
Data Index: 1219598 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.6618. Min Act: -0.1700
Data Index: 5561790 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.6306. Min Act: -0.1700
Data Index: 8222783 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.5681. Min Act: -0.1700
Data Index: 823867 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.5681. Min Act: -0.1700
Data Index: 1904550 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.5368. Min Act: -0.1700
Data Index: 6311359 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.5368. Min Act: -0.1700
Data Index: 2105013 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.5681. Min Act: -0.1700
Data Index: 4752094 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.5681. Min Act: -0.1700
Data Index: 5104809 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.5056. Min Act: -0.1700
Data Index: 3734079 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8806. Min Range: -5.8806
Max Act: 5.5056. Min Act: -0.1700
Data Index: 4259793 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19