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

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

Neuron 4084 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: 0.6515. Min Range: -0.6515

Max Act: 0.6515. Min Act: -0.0000

Data Index: 320899 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.6024. Min Act: -0.0000

Data Index: 757694 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1062690 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.5222. Min Act: -0.0000

Data Index: 650590 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.5068. Min Act: -0.0000

Data Index: 370210 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4892. Min Act: -0.0000

Data Index: 910664 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4564. Min Act: -0.0000

Data Index: 391378 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4476. Min Act: -0.0000

Data Index: 857109 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1020023 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4601. Min Act: -0.0000

Data Index: 14188 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4435. Min Act: -0.0000

Data Index: 299374 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4372. Min Act: -0.0000

Data Index: 276960 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4338. Min Act: -0.0000

Data Index: 840109 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1295366 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4236. Min Act: -0.0000

Data Index: 193235 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4103. Min Act: -0.0000

Data Index: 208132 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4245. Min Act: -0.0000

Data Index: 340887 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4216. Min Act: -0.0000

Data Index: 711509 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4209. Min Act: -0.0000

Data Index: 563551 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4018. Min Act: -0.0000

Data Index: 792868 (C4 (Web Text))

Max Activating Token Index: 856