Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 502 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.5516. Min Act: -0.1700
Data Index: 6006585 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.5204. Min Act: -0.1700
Data Index: 3610233 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.4266. Min Act: -0.1700
Data Index: 710822 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.3329. Min Act: -0.1700
Data Index: 2156057 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.3016. Min Act: -0.1700
Data Index: 5882717 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.2704. Min Act: -0.1700
Data Index: 3574999 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.2391. Min Act: -0.1700
Data Index: 175338 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.2704. Min Act: -0.1700
Data Index: 2117593 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.2391. Min Act: -0.1700
Data Index: 4402225 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.2391. Min Act: -0.1700
Data Index: 724763 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.2704. Min Act: -0.1700
Data Index: 3300309 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.1766. Min Act: -0.1700
Data Index: 4349921 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.1454. Min Act: -0.1700
Data Index: 6824944 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.1766. Min Act: -0.1700
Data Index: 7795653 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.1766. Min Act: -0.1700
Data Index: 5491177 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.1141. Min Act: -0.1700
Data Index: 7968192 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.1454. Min Act: -0.1700
Data Index: 8197399 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.1141. Min Act: -0.1700
Data Index: 5190670 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.0829. Min Act: -0.1700
Data Index: 6453889 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5516. Min Range: -5.5516
Max Act: 5.0829. Min Act: -0.1700
Data Index: 2915976 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19