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

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

Neuron 3115 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: 0.1587. Min Range: -0.1587

Max Act: 0.1587. Min Act: -0.0002

Data Index: 664560 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1523. Min Act: -0.0002

Data Index: 196215 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1422. Min Act: -0.0002

Data Index: 562853 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1425. Min Act: -0.0002

Data Index: 337819 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1368. Min Act: -0.0002

Data Index: 388016 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1291. Min Act: -0.0002

Data Index: 228090 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1393. Min Act: -0.0002

Data Index: 357705 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1360. Min Act: -0.0002

Data Index: 1187334 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1358. Min Act: -0.0002

Data Index: 755770 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1351. Min Act: -0.0002

Data Index: 1096817 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1327. Min Act: -0.0002

Data Index: 115285 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1304. Min Act: -0.0002

Data Index: 1013915 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1308. Min Act: -0.0002

Data Index: 934174 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1297. Min Act: -0.0002

Data Index: 781946 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1252. Min Act: -0.0002

Data Index: 640381 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1302. Min Act: -0.0002

Data Index: 145560 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1249. Min Act: -0.0002

Data Index: 225844 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1283. Min Act: -0.0002

Data Index: 1354551 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1356. Min Act: -0.0002

Data Index: 914984 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1269. Min Act: -0.0002

Data Index: 434820 (C4 (Web Text))

Max Activating Token Index: 400