Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.2871. Min Act: -0.1700
Data Index: 398161 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.2558. Min Act: -0.1700
Data Index: 5803733 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.2558. Min Act: -0.1700
Data Index: 7228206 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1933. Min Act: -0.1700
Data Index: 7654096 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.2245. Min Act: -0.1700
Data Index: 1810413 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.2245. Min Act: -0.1700
Data Index: 6849678 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1933. Min Act: -0.1700
Data Index: 7681825 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1620. Min Act: -0.1700
Data Index: 6775988 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1933. Min Act: -0.1700
Data Index: 8474482 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1620. Min Act: -0.1700
Data Index: 5452070 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1620. Min Act: -0.1700
Data Index: 903004 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1620. Min Act: -0.1700
Data Index: 2511767 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1308. Min Act: -0.1700
Data Index: 8355183 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.0995. Min Act: -0.1700
Data Index: 3982892 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1308. Min Act: -0.1700
Data Index: 489144 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1308. Min Act: -0.1700
Data Index: 5965491 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1308. Min Act: -0.1700
Data Index: 5704354 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1308. Min Act: -0.1700
Data Index: 2368683 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.0995. Min Act: -0.1700
Data Index: 3939138 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2871. Min Range: -4.2871
Max Act: 4.1308. Min Act: -0.1700
Data Index: 5838288 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19