Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.7358. Min Act: -0.1700
Data Index: 3381451 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.6733. Min Act: -0.1700
Data Index: 8630776 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.6108. Min Act: -0.1700
Data Index: 5937516 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.5170. Min Act: -0.1700
Data Index: 6519973 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.4858. Min Act: -0.1700
Data Index: 3164616 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.4545. Min Act: -0.1700
Data Index: 2829154 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.4858. Min Act: -0.1700
Data Index: 2063850 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.3608. Min Act: -0.1700
Data Index: 3648860 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.3920. Min Act: -0.1700
Data Index: 2473621 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.3608. Min Act: -0.1700
Data Index: 2620515 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.3295. Min Act: -0.1700
Data Index: 8790220 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.2983. Min Act: -0.1700
Data Index: 1619733 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.3295. Min Act: -0.1700
Data Index: 1811250 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.3295. Min Act: -0.1700
Data Index: 1733129 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.2983. Min Act: -0.1700
Data Index: 4382217 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.2983. Min Act: -0.1700
Data Index: 3214749 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.2358. Min Act: -0.1700
Data Index: 6268817 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.2045. Min Act: -0.1700
Data Index: 2529348 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.2045. Min Act: -0.1700
Data Index: 7899884 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7358. Min Range: -6.7358
Max Act: 6.1733. Min Act: -0.1700
Data Index: 1859284 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19