Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1796 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1513. Min Act: -0.0001

Data Index: 983660 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1367. Min Act: -0.0001

Data Index: 1180128 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1407. Min Act: -0.0001

Data Index: 588187 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1379. Min Act: -0.0001

Data Index: 340478 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1454. Min Act: -0.0001

Data Index: 27678 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1375. Min Act: -0.0001

Data Index: 425237 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1317. Min Act: -0.0001

Data Index: 518099 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1156927 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1333. Min Act: -0.0001

Data Index: 325847 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1288. Min Act: -0.0001

Data Index: 571606 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1055888 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1328. Min Act: -0.0001

Data Index: 687489 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1227. Min Act: -0.0001

Data Index: 612422 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1051507 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1252343 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1255. Min Act: -0.0001

Data Index: 510505 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1255087 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1179. Min Act: -0.0001

Data Index: 457057 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1109. Min Act: -0.0001

Data Index: 791833 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1200. Min Act: -0.0001

Data Index: 496957 (C4 (Web Text))

Max Activating Token Index: 683