Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 899 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.6965. Min Act: -0.0000

Data Index: 190734 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.7878. Min Act: -0.0000

Data Index: 1096636 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.6649. Min Act: -0.0000

Data Index: 582071 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.5909. Min Act: -0.0000

Data Index: 458942 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.6579. Min Act: -0.0000

Data Index: 1271210 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4353. Min Act: -0.0000

Data Index: 368307 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4535. Min Act: -0.0000

Data Index: 36290 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4343. Min Act: -0.0000

Data Index: 1037243 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.5552. Min Act: -0.0000

Data Index: 82590 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4092. Min Act: -0.0000

Data Index: 874693 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4820. Min Act: -0.0000

Data Index: 192554 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.3993. Min Act: -0.0000

Data Index: 749271 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4034. Min Act: -0.0000

Data Index: 793390 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4012. Min Act: -0.0000

Data Index: 1023749 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.3326. Min Act: -0.0000

Data Index: 397392 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4172. Min Act: -0.0000

Data Index: 448676 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4173. Min Act: -0.0000

Data Index: 617947 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.2757. Min Act: -0.0000

Data Index: 141145 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4038. Min Act: -0.0000

Data Index: 1190539 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 1.7878. Min Range: -1.7878

Max Act: 1.4737. Min Act: -0.0000

Data Index: 1220122 (C4 (Web Text))

Max Activating Token Index: 785