Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 172 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.2282. Min Act: -0.0000

Data Index: 89659 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1879. Min Act: -0.0000

Data Index: 862898 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1786. Min Act: -0.0000

Data Index: 367372 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1484656 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1582. Min Act: -0.0001

Data Index: 1531287 (Python Code)

Max Activating Token Index: 206

Text #5

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1489924 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1471. Min Act: -0.0000

Data Index: 725702 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1345383 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1379. Min Act: -0.0001

Data Index: 292854 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1400620 (Python Code)

Max Activating Token Index: 612

Text #10

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1242214 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1222. Min Act: -0.0001

Data Index: 1564427 (Python Code)

Max Activating Token Index: 513

Text #12

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1655308 (Python Code)

Max Activating Token Index: 455

Text #13

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1635530 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1014408 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1638985 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1176. Min Act: -0.0000

Data Index: 117020 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1476478 (Python Code)

Max Activating Token Index: 740

Text #18

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1069. Min Act: -0.0000

Data Index: 117349 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1153. Min Act: -0.0000

Data Index: 671248 (C4 (Web Text))

Max Activating Token Index: 861