Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1957 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.2351. Min Act: -0.0001

Data Index: 745369 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1419. Min Act: -0.0001

Data Index: 624570 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1593. Min Act: -0.0001

Data Index: 414772 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0707. Min Act: -0.0001

Data Index: 522526 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0213. Min Act: -0.0001

Data Index: 351761 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0527. Min Act: -0.0001

Data Index: 1174504 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1101. Min Act: -0.0001

Data Index: 24039 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0318. Min Act: -0.0002

Data Index: 874425 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0227. Min Act: -0.0001

Data Index: 1289959 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0305. Min Act: -0.0002

Data Index: 698776 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0896. Min Act: -0.0002

Data Index: 40533 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.9604. Min Act: -0.0002

Data Index: 250661 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.9623. Min Act: -0.0001

Data Index: 1200366 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0291. Min Act: -0.0001

Data Index: 639551 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.9980. Min Act: -0.0001

Data Index: 432896 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0258. Min Act: -0.0001

Data Index: 1088741 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0574. Min Act: -0.0001

Data Index: 1264273 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0582. Min Act: -0.0002

Data Index: 668157 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 1.2351. Min Range: -1.2351

Max Act: 0.9622. Min Act: -0.0001

Data Index: 1105296 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0102. Min Act: -0.0002

Data Index: 319766 (C4 (Web Text))

Max Activating Token Index: 378