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

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

Neuron 2365 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1632070 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1190190 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0263. Min Act: -0.0001

Data Index: 308235 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1506991 (Python Code)

Max Activating Token Index: 1010

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0257. Min Act: -0.0001

Data Index: 793778 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0268. Min Act: -0.0001

Data Index: 788781 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0261. Min Act: -0.0001

Data Index: 973472 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0242. Min Act: -0.0001

Data Index: 311052 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0266. Min Act: -0.0001

Data Index: 909442 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1430489 (Python Code)

Max Activating Token Index: 995

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1370110 (Python Code)

Max Activating Token Index: 998

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0221. Min Act: -0.0001

Data Index: 827846 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1653612 (Python Code)

Max Activating Token Index: 680

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1437919 (Python Code)

Max Activating Token Index: 1018

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0205. Min Act: -0.0001

Data Index: 426354 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1489899 (Python Code)

Max Activating Token Index: 998

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0207. Min Act: -0.0001

Data Index: 994495 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1244213 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0201. Min Act: -0.0001

Data Index: 192566 (C4 (Web Text))

Max Activating Token Index: 805