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

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

Neuron 4516 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1576. Min Act: -0.0002

Data Index: 103994 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1536. Min Act: -0.0002

Data Index: 862755 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1374. Min Act: -0.0002

Data Index: 1543990 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1416. Min Act: -0.0002

Data Index: 1601918 (Python Code)

Max Activating Token Index: 860

Text #4

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1303. Min Act: -0.0002

Data Index: 253619 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1151922 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1021270 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1282. Min Act: -0.0002

Data Index: 1325671 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1279. Min Act: -0.0002

Data Index: 630843 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1311. Min Act: -0.0002

Data Index: 640644 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1285. Min Act: -0.0002

Data Index: 877778 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1222. Min Act: -0.0002

Data Index: 1036590 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1262. Min Act: -0.0002

Data Index: 1486659 (Python Code)

Max Activating Token Index: 259

Text #13

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1361. Min Act: -0.0002

Data Index: 1376355 (Python Code)

Max Activating Token Index: 416

Text #14

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1314. Min Act: -0.0002

Data Index: 83787 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1454. Min Act: -0.0002

Data Index: 772600 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1330. Min Act: -0.0002

Data Index: 1229779 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1241. Min Act: -0.0002

Data Index: 263113 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1372. Min Act: -0.0003

Data Index: 48295 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1277. Min Act: -0.0002

Data Index: 460288 (C4 (Web Text))

Max Activating Token Index: 798