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

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

Neuron 4830 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1245062 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1350801 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0337. Min Act: -0.0000

Data Index: 884442 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0347. Min Act: -0.0000

Data Index: 721073 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0307. Min Act: -0.0000

Data Index: 327913 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0255. Min Act: -0.0000

Data Index: 145270 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0303. Min Act: -0.0000

Data Index: 448984 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0257. Min Act: -0.0000

Data Index: 1376550 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0262. Min Act: -0.0000

Data Index: 1426603 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1562537 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0257. Min Act: -0.0001

Data Index: 418180 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1546791 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0258. Min Act: -0.0000

Data Index: 1527127 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0248. Min Act: -0.0000

Data Index: 373502 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0235. Min Act: -0.0000

Data Index: 1387404 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0234. Min Act: -0.0000

Data Index: 1626917 (Python Code)

Max Activating Token Index: 145

Text #16

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0241. Min Act: -0.0000

Data Index: 1481157 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0239. Min Act: -0.0000

Data Index: 1604597 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0247. Min Act: -0.0000

Data Index: 944807 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0226. Min Act: -0.0000

Data Index: 195036 (C4 (Web Text))

Max Activating Token Index: 726