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

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

Neuron 3119 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1108527 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4590. Min Act: -0.0000

Data Index: 975141 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4470. Min Act: -0.0000

Data Index: 115268 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1114615 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1169124 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4242. Min Act: -0.0000

Data Index: 468496 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1196337 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1061737 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4196. Min Act: -0.0000

Data Index: 436677 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1022513 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1216503 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1196911 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4374. Min Act: -0.0000

Data Index: 522245 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1086725 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4195. Min Act: -0.0000

Data Index: 485136 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4270. Min Act: -0.0000

Data Index: 21779 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1066089 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3949. Min Act: -0.0000

Data Index: 367645 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4055. Min Act: -0.0000

Data Index: 469506 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4081. Min Act: -0.0000

Data Index: 566056 (C4 (Web Text))

Max Activating Token Index: 461