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

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

Neuron 3742 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: 1.2677. Min Range: -1.2677

Max Act: 1.2677. Min Act: -0.0000

Data Index: 303051 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.2666. Min Act: -0.0000

Data Index: 264907 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1217702 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.2005. Min Act: -0.0000

Data Index: 394023 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.2256. Min Act: -0.0000

Data Index: 1244364 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.2196. Min Act: -0.0000

Data Index: 299093 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.2285. Min Act: -0.0000

Data Index: 542264 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1011689 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1278816 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.1176. Min Act: -0.0000

Data Index: 336503 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.1356. Min Act: -0.0000

Data Index: 635442 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.1058. Min Act: -0.0000

Data Index: 441370 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.1668. Min Act: -0.0000

Data Index: 531832 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1136842 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.0866. Min Act: -0.0000

Data Index: 71929 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.1690. Min Act: -0.0000

Data Index: 307341 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.0950. Min Act: -0.0000

Data Index: 661562 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.0354. Min Act: -0.0000

Data Index: 987580 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.0337. Min Act: -0.0000

Data Index: 37927 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1094777 (C4 (Web Text))

Max Activating Token Index: 142