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

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

Neuron 4725 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: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0002

Data Index: 976176 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1568. Min Act: -0.0003

Data Index: 17372 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1568. Min Act: -0.0003

Data Index: 900514 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1543. Min Act: -0.0003

Data Index: 587537 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1499. Min Act: -0.0003

Data Index: 610102 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1409. Min Act: -0.0003

Data Index: 477743 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1401. Min Act: -0.0003

Data Index: 951295 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1420. Min Act: -0.0003

Data Index: 1197822 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1414. Min Act: -0.0003

Data Index: 276963 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1366. Min Act: -0.0003

Data Index: 1216305 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1383. Min Act: -0.0002

Data Index: 74303 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1431. Min Act: -0.0003

Data Index: 159389 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1382. Min Act: -0.0003

Data Index: 80862 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1382. Min Act: -0.0003

Data Index: 538025 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1370. Min Act: -0.0002

Data Index: 876271 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1321. Min Act: -0.0003

Data Index: 600942 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1316. Min Act: -0.0003

Data Index: 101530 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1360. Min Act: -0.0003

Data Index: 598714 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1411. Min Act: -0.0003

Data Index: 551531 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1336. Min Act: -0.0003

Data Index: 267959 (C4 (Web Text))

Max Activating Token Index: 259