Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0723. Min Range: -4.0723
Max Act: 4.0723. Min Act: -0.1700
Data Index: 5623720 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0723. Min Range: -4.0723
Max Act: 4.0097. Min Act: -0.1700
Data Index: 5970917 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.9160. Min Act: -0.1700
Data Index: 1774854 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.8534. Min Act: -0.1700
Data Index: 1841877 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7909. Min Act: -0.1700
Data Index: 8107260 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7596. Min Act: -0.1700
Data Index: 7232955 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7909. Min Act: -0.1700
Data Index: 4004681 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7909. Min Act: -0.1700
Data Index: 5475540 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7909. Min Act: -0.1700
Data Index: 6817418 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7909. Min Act: -0.1700
Data Index: 4961071 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7752. Min Act: -0.1700
Data Index: 686594 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7909. Min Act: -0.1700
Data Index: 2922750 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7283. Min Act: -0.1700
Data Index: 2822587 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7909. Min Act: -0.1700
Data Index: 8720986 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7283. Min Act: -0.1700
Data Index: 1204147 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7440. Min Act: -0.1700
Data Index: 932392 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7440. Min Act: -0.1700
Data Index: 2575105 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7596. Min Act: -0.1700
Data Index: 1012693 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.7283. Min Act: -0.1700
Data Index: 3627070 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0723. Min Range: -4.0723
Max Act: 3.6970. Min Act: -0.1700
Data Index: 4706018 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19