Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3032 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1206668 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1729. Min Act: -0.0000

Data Index: 303683 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1601944 (Python Code)

Max Activating Token Index: 938

Text #3

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1572. Min Act: -0.0000

Data Index: 939477 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1219974 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1472. Min Act: -0.0000

Data Index: 4402 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1331. Min Act: -0.0000

Data Index: 94604 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1268. Min Act: -0.0000

Data Index: 376215 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1399. Min Act: -0.0000

Data Index: 748703 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1290. Min Act: -0.0000

Data Index: 982282 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1164760 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1439952 (Python Code)

Max Activating Token Index: 932

Text #12

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1298. Min Act: -0.0000

Data Index: 18630 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1338. Min Act: -0.0000

Data Index: 367465 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1540217 (Python Code)

Max Activating Token Index: 324

Text #15

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1232. Min Act: -0.0000

Data Index: 697587 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1279. Min Act: -0.0000

Data Index: 322035 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1267. Min Act: -0.0000

Data Index: 823793 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1157663 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1439880 (Python Code)

Max Activating Token Index: 976