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

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

Neuron 2157 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1625. Min Act: -0.0001

Data Index: 619293 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1425. Min Act: -0.0001

Data Index: 205072 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1591. Min Act: -0.0001

Data Index: 362528 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1052729 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1515. Min Act: -0.0001

Data Index: 419364 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1398. Min Act: -0.0001

Data Index: 244814 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1368. Min Act: -0.0001

Data Index: 823361 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1435. Min Act: -0.0001

Data Index: 847084 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1090. Min Act: -0.0001

Data Index: 993563 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1111672 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1369. Min Act: -0.0001

Data Index: 134764 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1297342 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1297. Min Act: -0.0001

Data Index: 1376838 (Python Code)

Max Activating Token Index: 548

Text #13

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1288. Min Act: -0.0001

Data Index: 356894 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1225. Min Act: -0.0001

Data Index: 181590 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1330. Min Act: -0.0001

Data Index: 157555 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1477349 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1436593 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1283. Min Act: -0.0001

Data Index: 321410 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1594959 (Python Code)

Max Activating Token Index: 720