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

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

Neuron 3414 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1340078 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2756. Min Act: -0.0000

Data Index: 730488 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2708. Min Act: -0.0000

Data Index: 227829 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2641. Min Act: -0.0000

Data Index: 616639 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2710. Min Act: -0.0000

Data Index: 48171 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2517. Min Act: -0.0000

Data Index: 282166 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2478. Min Act: -0.0000

Data Index: 92635 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2507. Min Act: -0.0000

Data Index: 585377 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2426. Min Act: -0.0001

Data Index: 250495 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2421. Min Act: -0.0001

Data Index: 391445 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2382. Min Act: -0.0000

Data Index: 192722 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2375. Min Act: -0.0001

Data Index: 1060345 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2198. Min Act: -0.0001

Data Index: 614421 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1228334 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2223. Min Act: -0.0000

Data Index: 516344 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2273. Min Act: -0.0000

Data Index: 828309 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1210252 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2188. Min Act: -0.0000

Data Index: 681094 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2225. Min Act: -0.0000

Data Index: 305933 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1109515 (C4 (Web Text))

Max Activating Token Index: 667