Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2968 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.5444. Min Act: -0.0001

Data Index: 1226693 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.3715. Min Act: -0.0001

Data Index: 1181144 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2970. Min Act: -0.0001

Data Index: 84462 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2270. Min Act: -0.0001

Data Index: 955885 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1854. Min Act: -0.0001

Data Index: 1135544 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2221. Min Act: -0.0001

Data Index: 507697 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1909. Min Act: -0.0001

Data Index: 19605 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2464. Min Act: -0.0001

Data Index: 1145816 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1354. Min Act: -0.0001

Data Index: 373814 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0626. Min Act: -0.0001

Data Index: 727980 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2005. Min Act: -0.0001

Data Index: 848408 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0433. Min Act: -0.0001

Data Index: 1067657 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0413. Min Act: -0.0001

Data Index: 487728 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0380. Min Act: -0.0001

Data Index: 547430 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0927. Min Act: -0.0001

Data Index: 481049 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0620. Min Act: -0.0001

Data Index: 110261 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0886. Min Act: -0.0001

Data Index: 623238 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.5444. Min Range: -1.5444

Max Act: 0.9943. Min Act: -0.0001

Data Index: 754218 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0581. Min Act: -0.0001

Data Index: 707815 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.0197. Min Act: -0.0001

Data Index: 496792 (C4 (Web Text))

Max Activating Token Index: 526