Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4762 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.2283. Min Act: -0.0000

Data Index: 807496 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.1482. Min Act: -0.0000

Data Index: 724091 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 3.2283. Min Range: -3.2283

Max Act: 3.0982. Min Act: -0.0000

Data Index: 941481 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.7270. Min Act: -0.0000

Data Index: 933540 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.6492. Min Act: -0.0000

Data Index: 349186 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.6205. Min Act: -0.0000

Data Index: 1142394 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.5591. Min Act: -0.0000

Data Index: 682874 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.6636. Min Act: -0.0000

Data Index: 641168 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.5189. Min Act: -0.0000

Data Index: 93348 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.4801. Min Act: -0.0000

Data Index: 763600 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.2138. Min Act: -0.0000

Data Index: 343177 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.4718. Min Act: -0.0000

Data Index: 113830 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.4361. Min Act: -0.0000

Data Index: 325167 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.4425. Min Act: -0.0000

Data Index: 875617 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.2967. Min Act: -0.0000

Data Index: 1061118 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.4058. Min Act: -0.0000

Data Index: 640022 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1177962 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.3436. Min Act: -0.0000

Data Index: 463350 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.2237. Min Act: -0.0000

Data Index: 1282334 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 3.2283. Min Range: -3.2283

Max Act: 2.4935. Min Act: -0.0000

Data Index: 334696 (C4 (Web Text))

Max Activating Token Index: 297