Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2364 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.7380. Min Act: -0.1700
Data Index: 4016885 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.7220. Min Act: -0.1700
Data Index: 5336667 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.6900. Min Act: -0.1700
Data Index: 2795331 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.6580. Min Act: -0.1700
Data Index: 1037840 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.6740. Min Act: -0.1700
Data Index: 2793710 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5776. Min Act: -0.1700
Data Index: 7789298 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5937. Min Act: -0.1700
Data Index: 1222991 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.6258. Min Act: -0.1700
Data Index: 116461 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5937. Min Act: -0.1700
Data Index: 4263612 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5776. Min Act: -0.1700
Data Index: 7761637 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5776. Min Act: -0.1700
Data Index: 1502751 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5776. Min Act: -0.1700
Data Index: 7798014 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5937. Min Act: -0.1700
Data Index: 4796906 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5614. Min Act: -0.1700
Data Index: 5302425 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5776. Min Act: -0.1700
Data Index: 1265799 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5614. Min Act: -0.1700
Data Index: 7780643 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5453. Min Act: -0.1700
Data Index: 8534170 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5291. Min Act: -0.1700
Data Index: 1281935 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5291. Min Act: -0.1700
Data Index: 1134409 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7380. Min Range: -2.7380
Max Act: 2.5291. Min Act: -0.1700
Data Index: 1831653 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19