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

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

Neuron 3776 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1821. Min Act: -0.0001

Data Index: 468587 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1263399 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1204185 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1441. Min Act: -0.0001

Data Index: 554440 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1448. Min Act: -0.0000

Data Index: 487526 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1214153 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1365. Min Act: -0.0001

Data Index: 750844 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1387. Min Act: -0.0001

Data Index: 133535 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1328. Min Act: -0.0000

Data Index: 506001 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1198. Min Act: -0.0000

Data Index: 452168 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1249. Min Act: -0.0000

Data Index: 948985 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1228269 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1319. Min Act: -0.0001

Data Index: 974004 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1012645 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1193. Min Act: -0.0001

Data Index: 507661 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1319. Min Act: -0.0000

Data Index: 310516 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1224090 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1131. Min Act: -0.0001

Data Index: 719245 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1090007 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1297. Min Act: -0.0001

Data Index: 106776 (C4 (Web Text))

Max Activating Token Index: 411