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

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

Neuron 1007 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.3002. Min Act: -0.0002

Data Index: 1309801 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2804. Min Act: -0.0003

Data Index: 1148733 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2719. Min Act: -0.0003

Data Index: 758234 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2653. Min Act: -0.0002

Data Index: 128522 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2491. Min Act: -0.0002

Data Index: 1268970 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2585. Min Act: -0.0002

Data Index: 1067909 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2459. Min Act: -0.0002

Data Index: 754816 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2425. Min Act: -0.0002

Data Index: 878056 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2322. Min Act: -0.0002

Data Index: 821179 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2346. Min Act: -0.0003

Data Index: 721209 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2343. Min Act: -0.0002

Data Index: 581891 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2309. Min Act: -0.0002

Data Index: 1344387 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2318. Min Act: -0.0002

Data Index: 670132 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2214. Min Act: -0.0003

Data Index: 1062692 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2276. Min Act: -0.0003

Data Index: 96130 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2277. Min Act: -0.0002

Data Index: 424779 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2281. Min Act: -0.0002

Data Index: 531566 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2328. Min Act: -0.0003

Data Index: 43847 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2224. Min Act: -0.0002

Data Index: 874133 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.2184. Min Act: -0.0003

Data Index: 549230 (C4 (Web Text))

Max Activating Token Index: 934