Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4093 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.8871. Min Act: -0.1700
Data Index: 2342408 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.6996. Min Act: -0.1700
Data Index: 3063696 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.6996. Min Act: -0.1700
Data Index: 1616834 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.6996. Min Act: -0.1700
Data Index: 7721281 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.6996. Min Act: -0.1700
Data Index: 7771374 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.6684. Min Act: -0.1700
Data Index: 5935591 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.5746. Min Act: -0.1700
Data Index: 7908882 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.6059. Min Act: -0.1700
Data Index: 4517911 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.5434. Min Act: -0.1700
Data Index: 6364710 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.5121. Min Act: -0.1700
Data Index: 3357214 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.5121. Min Act: -0.1700
Data Index: 573483 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.5121. Min Act: -0.1700
Data Index: 983762 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.5121. Min Act: -0.1700
Data Index: 3898944 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.5121. Min Act: -0.1700
Data Index: 3137728 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.4809. Min Act: -0.1700
Data Index: 1915346 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.5121. Min Act: -0.1700
Data Index: 998554 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.4809. Min Act: -0.1700
Data Index: 101216 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.4496. Min Act: -0.1700
Data Index: 1446537 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.4809. Min Act: -0.1700
Data Index: 2802290 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8871. Min Range: -5.8871
Max Act: 5.4496. Min Act: -0.1700
Data Index: 3797069 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19