Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1628 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.9417. Min Act: -0.1700
Data Index: 2580616 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.9417. Min Act: -0.1700
Data Index: 5322310 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0042. Min Range: -8.0042
Max Act: 8.0042. Min Act: -0.1700
Data Index: 613962 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0042. Min Range: -8.0042
Max Act: 8.0042. Min Act: -0.1700
Data Index: 3198407 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0042. Min Range: -8.0042
Max Act: 8.0042. Min Act: -0.1700
Data Index: 569560 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8792. Min Act: -0.1700
Data Index: 8708622 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.9417. Min Act: -0.1700
Data Index: 5694806 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8167. Min Act: -0.1700
Data Index: 8038252 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8792. Min Act: -0.1700
Data Index: 6552687 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8792. Min Act: -0.1700
Data Index: 4430191 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8792. Min Act: -0.1700
Data Index: 5261583 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8792. Min Act: -0.1700
Data Index: 2945897 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8792. Min Act: -0.1700
Data Index: 5495514 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8167. Min Act: -0.1700
Data Index: 2536608 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.7542. Min Act: -0.1700
Data Index: 2633180 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8167. Min Act: -0.1700
Data Index: 7404885 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8167. Min Act: -0.1700
Data Index: 2851279 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.7542. Min Act: -0.1700
Data Index: 2750957 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.8167. Min Act: -0.1700
Data Index: 8049913 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0042. Min Range: -8.0042
Max Act: 7.6917. Min Act: -0.1700
Data Index: 1147021 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19