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

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

Neuron 768 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0472. Min Act: -0.0002

Data Index: 745738 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0357. Min Act: -0.0002

Data Index: 828936 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0319. Min Act: -0.0002

Data Index: 297754 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1303788 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0286. Min Act: -0.0002

Data Index: 877528 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0272. Min Act: -0.0002

Data Index: 387761 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1237496 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0258. Min Act: -0.0002

Data Index: 647962 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0257. Min Act: -0.0002

Data Index: 41894 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0226. Min Act: -0.0002

Data Index: 449823 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1288152 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1020456 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1303618 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0228. Min Act: -0.0002

Data Index: 119280 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0222. Min Act: -0.0002

Data Index: 570367 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0213. Min Act: -0.0002

Data Index: 364250 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0218. Min Act: -0.0002

Data Index: 678759 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1191382 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0220. Min Act: -0.0002

Data Index: 242620 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1325062 (C4 (Web Text))

Max Activating Token Index: 347