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

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

Neuron 662 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0002

Data Index: 664807 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0246. Min Act: -0.0003

Data Index: 729953 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0245. Min Act: -0.0002

Data Index: 965075 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0230. Min Act: -0.0002

Data Index: 181864 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1149317 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0218. Min Act: -0.0002

Data Index: 518407 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0218. Min Act: -0.0002

Data Index: 452812 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0224. Min Act: -0.0003

Data Index: 822299 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1342288 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0218. Min Act: -0.0002

Data Index: 957376 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1203852 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0217. Min Act: -0.0003

Data Index: 498839 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0213. Min Act: -0.0002

Data Index: 733367 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0221. Min Act: -0.0003

Data Index: 264469 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0207. Min Act: -0.0003

Data Index: 568356 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0209. Min Act: -0.0002

Data Index: 840883 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0210. Min Act: -0.0003

Data Index: 719652 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1024255 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0208. Min Act: -0.0002

Data Index: 405858 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0206. Min Act: -0.0003

Data Index: 674453 (C4 (Web Text))

Max Activating Token Index: 616