Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1799 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0004

Data Index: 778130 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1290784 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0350. Min Act: -0.0003

Data Index: 43388 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1273580 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0329. Min Act: -0.0003

Data Index: 778646 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0327. Min Act: -0.0003

Data Index: 270900 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1331365 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1340200 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0274. Min Act: -0.0003

Data Index: 882343 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0307. Min Act: -0.0003

Data Index: 537557 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1249591 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0310. Min Act: -0.0003

Data Index: 275169 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0315. Min Act: -0.0003

Data Index: 408743 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0289. Min Act: -0.0003

Data Index: 873808 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0293. Min Act: -0.0003

Data Index: 983852 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0286. Min Act: -0.0003

Data Index: 283089 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0291. Min Act: -0.0003

Data Index: 139007 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0300. Min Act: -0.0003

Data Index: 524880 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0270. Min Act: -0.0003

Data Index: 2718 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0283. Min Act: -0.0003

Data Index: 810014 (C4 (Web Text))

Max Activating Token Index: 881