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

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

Neuron 510 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: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0000

Data Index: 425246 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1375663 (Python Code)

Max Activating Token Index: 727

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1535389 (Python Code)

Max Activating Token Index: 646

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1475175 (Python Code)

Max Activating Token Index: 376

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1469507 (Python Code)

Max Activating Token Index: 498

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1495256 (Python Code)

Max Activating Token Index: 474

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1580069 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1195. Min Act: -0.0000

Data Index: 96138 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1599713 (Python Code)

Max Activating Token Index: 427

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1622841 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1047. Min Act: -0.0000

Data Index: 686265 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1612344 (Python Code)

Max Activating Token Index: 446

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1177. Min Act: -0.0000

Data Index: 860452 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1436171 (Python Code)

Max Activating Token Index: 195

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1147. Min Act: -0.0000

Data Index: 999576 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1636068 (Python Code)

Max Activating Token Index: 151

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1402132 (Python Code)

Max Activating Token Index: 562

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1516795 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1229. Min Act: -0.0000

Data Index: 434317 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1607312 (Python Code)

Max Activating Token Index: 336