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

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

Neuron 347 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: 4.7289. Min Range: -4.7289

Max Act: 4.7289. Min Act: -0.0000

Data Index: 713103 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 4.7289. Min Range: -4.7289

Max Act: 4.3595. Min Act: -0.0000

Data Index: 522503 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 4.7289. Min Range: -4.7289

Max Act: 4.0762. Min Act: -0.0001

Data Index: 403617 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 4.7289. Min Range: -4.7289

Max Act: 4.2353. Min Act: -0.0000

Data Index: 544419 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.9245. Min Act: -0.0000

Data Index: 278009 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.9178. Min Act: -0.0000

Data Index: 825497 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.8929. Min Act: -0.0000

Data Index: 272953 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.7280. Min Act: -0.0000

Data Index: 952537 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.5725. Min Act: -0.0000

Data Index: 176106 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.8664. Min Act: -0.0000

Data Index: 1359591 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 4.7289. Min Range: -4.7289

Max Act: 4.0244. Min Act: -0.0000

Data Index: 536413 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.8595. Min Act: -0.0001

Data Index: 1236864 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.5715. Min Act: -0.0000

Data Index: 882227 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.5692. Min Act: -0.0000

Data Index: 1125695 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.7177. Min Act: -0.0000

Data Index: 69193 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.6916. Min Act: -0.0000

Data Index: 585460 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.3481. Min Act: -0.0000

Data Index: 314657 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.9031. Min Act: -0.0000

Data Index: 1149689 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.5834. Min Act: -0.0000

Data Index: 118263 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 4.7289. Min Range: -4.7289

Max Act: 3.5738. Min Act: -0.0000

Data Index: 287350 (C4 (Web Text))

Max Activating Token Index: 355