Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 853 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1204. Min Range: -8.1204
Max Act: 8.1204. Min Act: -0.1700
Data Index: 42259 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1204. Min Range: -8.1204
Max Act: 7.5266. Min Act: -0.1700
Data Index: 7804975 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1204. Min Range: -8.1204
Max Act: 7.2141. Min Act: -0.1700
Data Index: 5357906 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1204. Min Range: -8.1204
Max Act: 7.1516. Min Act: -0.1700
Data Index: 1043722 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1204. Min Range: -8.1204
Max Act: 7.1829. Min Act: -0.1700
Data Index: 2170292 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.9954. Min Act: -0.1700
Data Index: 4320136 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.9641. Min Act: -0.1700
Data Index: 3321020 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.9329. Min Act: -0.1700
Data Index: 3855045 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.9954. Min Act: -0.1700
Data Index: 2992132 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.9016. Min Act: -0.1700
Data Index: 6150478 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.8704. Min Act: -0.1700
Data Index: 6226605 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.9016. Min Act: -0.1700
Data Index: 5625820 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.8704. Min Act: -0.1700
Data Index: 949579 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.8391. Min Act: -0.1700
Data Index: 1815872 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.7766. Min Act: -0.1699
Data Index: 2170272 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.8391. Min Act: -0.1700
Data Index: 7230506 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.7454. Min Act: -0.1700
Data Index: 2170280 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.8079. Min Act: -0.1700
Data Index: 4735905 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.7766. Min Act: -0.1700
Data Index: 2170278 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1204. Min Range: -8.1204
Max Act: 6.7454. Min Act: -0.1700
Data Index: 783043 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19