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

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

Neuron 2418 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7611. Min Act: -0.0000

Data Index: 645388 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7689. Min Act: -0.0000

Data Index: 501642 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7196. Min Act: -0.0000

Data Index: 593434 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6719. Min Act: -0.0000

Data Index: 852437 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6769. Min Act: -0.0000

Data Index: 769748 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.7097. Min Act: -0.0000

Data Index: 57686 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5942. Min Act: -0.0000

Data Index: 651770 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6738. Min Act: -0.0000

Data Index: 536257 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1102137 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6274. Min Act: -0.0000

Data Index: 435811 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5958. Min Act: -0.0000

Data Index: 619944 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1317976 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5921. Min Act: -0.0000

Data Index: 705587 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1195477 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5331. Min Act: -0.0000

Data Index: 160491 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1281263 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1166512 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5397. Min Act: -0.0000

Data Index: 360600 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1007694 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.7689. Min Range: -0.7689

Max Act: 0.5493. Min Act: -0.0000

Data Index: 385814 (C4 (Web Text))

Max Activating Token Index: 628