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

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

Neuron 1316 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0541. Min Act: -0.0002

Data Index: 797449 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0461. Min Act: -0.0002

Data Index: 908079 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0451. Min Act: -0.0002

Data Index: 529789 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0425. Min Act: -0.0002

Data Index: 147568 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0438. Min Act: -0.0002

Data Index: 682694 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0433. Min Act: -0.0002

Data Index: 446330 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1285187 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0429. Min Act: -0.0002

Data Index: 4706 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0393. Min Act: -0.0002

Data Index: 189538 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1039368 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0401. Min Act: -0.0002

Data Index: 444307 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0385. Min Act: -0.0002

Data Index: 793127 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0388. Min Act: -0.0002

Data Index: 571255 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1064576 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0384. Min Act: -0.0002

Data Index: 294500 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0378. Min Act: -0.0002

Data Index: 115132 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0374. Min Act: -0.0002

Data Index: 723385 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0374. Min Act: -0.0002

Data Index: 426342 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0380. Min Act: -0.0002

Data Index: 165965 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0368. Min Act: -0.0002

Data Index: 83146 (C4 (Web Text))

Max Activating Token Index: 114