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

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

Neuron 2596 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0003

Data Index: 765255 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0429. Min Act: -0.0003

Data Index: 104273 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1030677 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0434. Min Act: -0.0003

Data Index: 171901 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0374. Min Act: -0.0003

Data Index: 383376 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0384. Min Act: -0.0003

Data Index: 24555 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1552392 (Python Code)

Max Activating Token Index: 381

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1227333 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1221845 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1265345 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1590186 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1337996 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0328. Min Act: -0.0003

Data Index: 732581 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0328. Min Act: -0.0003

Data Index: 315734 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0336. Min Act: -0.0003

Data Index: 416049 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0337. Min Act: -0.0003

Data Index: 823537 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1633375 (Python Code)

Max Activating Token Index: 831

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1596600 (Python Code)

Max Activating Token Index: 329

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0284. Min Act: -0.0003

Data Index: 684794 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0283. Min Act: -0.0003

Data Index: 959908 (C4 (Web Text))

Max Activating Token Index: 887