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

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

Neuron 5955 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: 0.1523. Min Range: -0.1523

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1548243 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1345407 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1007789 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1328. Min Act: -0.0001

Data Index: 166308 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1074287 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1145658 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1278. Min Act: -0.0001

Data Index: 636339 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1294. Min Act: -0.0001

Data Index: 344251 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1280432 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1248. Min Act: -0.0001

Data Index: 410674 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1195. Min Act: -0.0000

Data Index: 225660 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1261. Min Act: -0.0001

Data Index: 514323 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1290. Min Act: -0.0001

Data Index: 903433 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1245. Min Act: -0.0000

Data Index: 81344 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1139. Min Act: -0.0001

Data Index: 179503 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1110. Min Act: -0.0001

Data Index: 172972 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1181836 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1202. Min Act: -0.0000

Data Index: 314162 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1009. Min Act: -0.0000

Data Index: 851526 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1362544 (Python Code)

Max Activating Token Index: 10