Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3354 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1923. Min Act: -0.0001

Data Index: 389113 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1760. Min Act: -0.0000

Data Index: 61466 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1033420 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1409. Min Act: -0.0001

Data Index: 252047 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1387. Min Act: -0.0001

Data Index: 696152 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1290. Min Act: -0.0000

Data Index: 90798 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1037439 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1264. Min Act: -0.0001

Data Index: 1219652 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1295. Min Act: -0.0000

Data Index: 708128 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1309. Min Act: -0.0000

Data Index: 426039 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1279477 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1251. Min Act: -0.0001

Data Index: 853054 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1263. Min Act: -0.0001

Data Index: 701906 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1304. Min Act: -0.0000

Data Index: 291854 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1206. Min Act: -0.0000

Data Index: 704823 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1283. Min Act: -0.0000

Data Index: 103146 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1225. Min Act: -0.0000

Data Index: 817425 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1227. Min Act: -0.0000

Data Index: 499879 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1205. Min Act: -0.0000

Data Index: 756446 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1151. Min Act: -0.0001

Data Index: 395871 (C4 (Web Text))

Max Activating Token Index: 290