Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 691 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0003

Data Index: 4047 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1023977 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0373. Min Act: -0.0003

Data Index: 939930 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0338. Min Act: -0.0003

Data Index: 286624 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1038619 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1547446 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1365498 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1042598 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1627835 (Python Code)

Max Activating Token Index: 1004

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0254. Min Act: -0.0003

Data Index: 327592 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1567070 (Python Code)

Max Activating Token Index: 1016

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1380361 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1373837 (Python Code)

Max Activating Token Index: 759

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1489950 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1441823 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1523119 (Python Code)

Max Activating Token Index: 984

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1630917 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1378223 (Python Code)

Max Activating Token Index: 1019

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1390752 (Python Code)

Max Activating Token Index: 985

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0205. Min Act: -0.0003

Data Index: 948252 (C4 (Web Text))

Max Activating Token Index: 1023