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

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

Neuron 2060 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1558725 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1450499 (Python Code)

Max Activating Token Index: 696

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1453268 (Python Code)

Max Activating Token Index: 530

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0352. Min Act: -0.0002

Data Index: 884701 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1560886 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1529703 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1588862 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1591022 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0332. Min Act: -0.0002

Data Index: 210838 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1646564 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1647519 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1519252 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1455240 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1381951 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1650879 (Python Code)

Max Activating Token Index: 490

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1378383 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1399347 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1463613 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1401338 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1611015 (Python Code)

Max Activating Token Index: 128