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

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

Neuron 145 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0395. Min Act: -0.0000

Data Index: 236021 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0317. Min Act: -0.0000

Data Index: 523918 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1019460 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0296. Min Act: -0.0000

Data Index: 205100 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0297. Min Act: -0.0000

Data Index: 763076 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0292. Min Act: -0.0000

Data Index: 342579 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0268. Min Act: -0.0000

Data Index: 1589145 (Python Code)

Max Activating Token Index: 924

Text #7

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0267. Min Act: -0.0000

Data Index: 609745 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0255. Min Act: -0.0000

Data Index: 1026942 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0274. Min Act: -0.0000

Data Index: 153616 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0270. Min Act: -0.0000

Data Index: 664058 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0268. Min Act: -0.0000

Data Index: 87384 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0244. Min Act: -0.0000

Data Index: 615031 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0252. Min Act: -0.0000

Data Index: 4922 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0257. Min Act: -0.0000

Data Index: 1132521 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0229. Min Act: 0.0000

Data Index: 119788 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0237. Min Act: -0.0000

Data Index: 331489 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0249. Min Act: -0.0000

Data Index: 1626943 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0236. Min Act: -0.0000

Data Index: 1033982 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0227. Min Act: -0.0000

Data Index: 209738 (C4 (Web Text))

Max Activating Token Index: 228