Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.4863. Min Act: -0.1700
Data Index: 4339016 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.4238. Min Act: -0.1700
Data Index: 8387713 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.3925. Min Act: -0.1700
Data Index: 3683314 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.2988. Min Act: -0.1700
Data Index: 4583301 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.2988. Min Act: -0.1700
Data Index: 8512866 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.2050. Min Act: -0.1700
Data Index: 542860 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.2363. Min Act: -0.1700
Data Index: 4797822 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.1738. Min Act: -0.1700
Data Index: 7668204 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.2050. Min Act: -0.1700
Data Index: 1391034 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.2050. Min Act: -0.1700
Data Index: 6949799 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.1425. Min Act: -0.1700
Data Index: 6578375 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.1738. Min Act: -0.1700
Data Index: 6338528 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.1425. Min Act: -0.1700
Data Index: 3738265 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.1113. Min Act: -0.1700
Data Index: 6739923 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.1113. Min Act: -0.1700
Data Index: 3668980 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.1425. Min Act: -0.1700
Data Index: 1590440 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.0800. Min Act: -0.1700
Data Index: 1275479 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.0800. Min Act: -0.1700
Data Index: 6525845 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.0800. Min Act: -0.1700
Data Index: 2339192 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4863. Min Range: -6.4863
Max Act: 6.0488. Min Act: -0.1700
Data Index: 7939201 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19