Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 720 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3702. Min Act: -0.0001

Data Index: 164566 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3121. Min Act: -0.0001

Data Index: 655960 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2672. Min Act: -0.0001

Data Index: 806694 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2396. Min Act: -0.0001

Data Index: 786053 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2277. Min Act: -0.0001

Data Index: 1199342 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2357. Min Act: -0.0001

Data Index: 1290222 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2246. Min Act: -0.0001

Data Index: 95812 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2419. Min Act: -0.0001

Data Index: 1097511 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2667. Min Act: -0.0001

Data Index: 1034337 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2275. Min Act: -0.0001

Data Index: 1228304 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1235327 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2214. Min Act: -0.0001

Data Index: 1053386 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2199. Min Act: -0.0001

Data Index: 140201 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2161. Min Act: -0.0001

Data Index: 602835 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2121. Min Act: -0.0001

Data Index: 233456 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1334908 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2112. Min Act: -0.0001

Data Index: 981776 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2005. Min Act: -0.0001

Data Index: 282640 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.1844. Min Act: -0.0001

Data Index: 528003 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.1972. Min Act: -0.0001

Data Index: 398139 (C4 (Web Text))

Max Activating Token Index: 721