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

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

Neuron 3040 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: 0.0408. Min Range: -0.0408

Max Act: 0.0408. Min Act: -0.0003

Data Index: 192391 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0399. Min Act: -0.0003

Data Index: 353113 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1226075 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0367. Min Act: -0.0002

Data Index: 507215 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1399213 (Python Code)

Max Activating Token Index: 224

Text #5

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1261145 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0345. Min Act: -0.0003

Data Index: 621736 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1616695 (Python Code)

Max Activating Token Index: 175

Text #8

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0329. Min Act: -0.0002

Data Index: 884867 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0328. Min Act: -0.0003

Data Index: 384410 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0321. Min Act: -0.0003

Data Index: 213267 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1453107 (Python Code)

Max Activating Token Index: 764

Text #12

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1265420 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0322. Min Act: -0.0002

Data Index: 622497 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0317. Min Act: -0.0003

Data Index: 99807 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1090546 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1472080 (Python Code)

Max Activating Token Index: 793

Text #17

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1642872 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0303. Min Act: -0.0003

Data Index: 951971 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0309. Min Act: -0.0003

Data Index: 552766 (C4 (Web Text))

Max Activating Token Index: 477