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

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

Neuron 99 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1272228 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1541. Min Act: -0.0002

Data Index: 854198 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1396. Min Act: -0.0002

Data Index: 277296 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1390. Min Act: -0.0002

Data Index: 634115 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1374. Min Act: -0.0002

Data Index: 775417 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1288. Min Act: -0.0002

Data Index: 820830 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1213. Min Act: -0.0002

Data Index: 291604 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1217. Min Act: -0.0001

Data Index: 595261 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1332235 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1320025 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1158. Min Act: -0.0002

Data Index: 709921 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1236. Min Act: -0.0002

Data Index: 971995 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1056874 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1187. Min Act: -0.0001

Data Index: 876487 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1235. Min Act: -0.0002

Data Index: 826296 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1231. Min Act: -0.0001

Data Index: 695147 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1224. Min Act: -0.0001

Data Index: 14161 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1226. Min Act: -0.0002

Data Index: 896630 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1247. Min Act: -0.0001

Data Index: 909255 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1204. Min Act: -0.0001

Data Index: 391096 (C4 (Web Text))

Max Activating Token Index: 415