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

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

Neuron 3904 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0589. Min Range: -2.0589

Max Act: 2.0589. Min Act: -0.0000

Data Index: 402045 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.6586. Min Act: -0.0000

Data Index: 919621 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.6189. Min Act: -0.0000

Data Index: 111778 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.6877. Min Act: -0.0000

Data Index: 1054636 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.4874. Min Act: -0.0000

Data Index: 1223097 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.5188. Min Act: -0.0000

Data Index: 818214 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.5483. Min Act: -0.0000

Data Index: 986619 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.5380. Min Act: -0.0000

Data Index: 197124 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.5187. Min Act: -0.0000

Data Index: 1068864 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.5145. Min Act: -0.0000

Data Index: 1131501 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.4738. Min Act: -0.0000

Data Index: 511820 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.4097. Min Act: -0.0000

Data Index: 664351 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.4023. Min Act: -0.0000

Data Index: 79072 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.3897. Min Act: -0.0000

Data Index: 638190 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.3830. Min Act: -0.0000

Data Index: 1252762 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.2639. Min Act: -0.0000

Data Index: 1127506 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.2687. Min Act: -0.0000

Data Index: 694671 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.3476. Min Act: -0.0000

Data Index: 619888 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.3968. Min Act: -0.0000

Data Index: 332388 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 2.0589. Min Range: -2.0589

Max Act: 1.2263. Min Act: -0.0000

Data Index: 194847 (C4 (Web Text))

Max Activating Token Index: 732