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

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

Neuron 1308 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.6316. Min Act: -0.0000

Data Index: 627357 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1255150 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.5304. Min Act: -0.0000

Data Index: 160600 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4646. Min Act: -0.0000

Data Index: 715700 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4820. Min Act: -0.0000

Data Index: 612147 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4616. Min Act: -0.0000

Data Index: 42089 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1324170 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1168665 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4686. Min Act: -0.0000

Data Index: 682275 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4354. Min Act: -0.0000

Data Index: 960225 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4263. Min Act: -0.0000

Data Index: 675320 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4342. Min Act: -0.0000

Data Index: 584927 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4321. Min Act: -0.0000

Data Index: 18859 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1091794 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4248. Min Act: -0.0000

Data Index: 62186 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4382. Min Act: -0.0000

Data Index: 87928 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1058014 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1052868 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4078. Min Act: -0.0000

Data Index: 946210 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1002832 (C4 (Web Text))

Max Activating Token Index: 996