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

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

Neuron 805 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: 0.1573. Min Range: -0.1573

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1581114 (Python Code)

Max Activating Token Index: 787

Text #1

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1545. Min Act: -0.0001

Data Index: 789451 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1560. Min Act: -0.0001

Data Index: 764207 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1452. Min Act: -0.0001

Data Index: 907779 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1479651 (Python Code)

Max Activating Token Index: 935

Text #5

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1457. Min Act: -0.0001

Data Index: 225571 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1408. Min Act: -0.0001

Data Index: 810047 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1365. Min Act: -0.0001

Data Index: 134873 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1226983 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1289. Min Act: -0.0001

Data Index: 387592 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1176604 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1328. Min Act: -0.0001

Data Index: 191959 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1357. Min Act: -0.0001

Data Index: 525839 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1286759 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1390. Min Act: -0.0001

Data Index: 96217 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1244. Min Act: -0.0001

Data Index: 270658 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1335. Min Act: -0.0001

Data Index: 362847 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1349. Min Act: -0.0001

Data Index: 391106 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1064916 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1219. Min Act: -0.0001

Data Index: 618677 (C4 (Web Text))

Max Activating Token Index: 7