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

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

Neuron 3902 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2512. Min Act: -0.0002

Data Index: 1014677 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2556. Min Act: -0.0002

Data Index: 496678 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.1924. Min Act: -0.0002

Data Index: 197908 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2636. Min Act: -0.0002

Data Index: 830214 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2568. Min Act: -0.0002

Data Index: 435734 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2313. Min Act: -0.0002

Data Index: 928895 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2479. Min Act: -0.0002

Data Index: 9166 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2125. Min Act: -0.0002

Data Index: 550907 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2121. Min Act: -0.0002

Data Index: 1156953 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2132. Min Act: -0.0002

Data Index: 267363 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2417. Min Act: -0.0002

Data Index: 646128 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2305. Min Act: -0.0002

Data Index: 768330 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2473. Min Act: -0.0002

Data Index: 317558 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2263. Min Act: -0.0002

Data Index: 1108 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2535. Min Act: -0.0002

Data Index: 382967 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2342. Min Act: -0.0002

Data Index: 252146 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2333. Min Act: -0.0002

Data Index: 134129 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2154. Min Act: -0.0002

Data Index: 700537 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2254. Min Act: -0.0002

Data Index: 1098934 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.2636. Min Range: -0.2636

Max Act: 0.2262. Min Act: -0.0002

Data Index: 594234 (C4 (Web Text))

Max Activating Token Index: 194