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

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

Neuron 553 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: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0003

Data Index: 347973 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0003

Data Index: 733626 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0357. Min Act: -0.0003

Data Index: 801281 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0348. Min Act: -0.0003

Data Index: 506999 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0345. Min Act: -0.0003

Data Index: 984129 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1351990 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0320. Min Act: -0.0003

Data Index: 646022 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0316. Min Act: -0.0003

Data Index: 14628 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0310. Min Act: -0.0003

Data Index: 981852 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1047104 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0309. Min Act: -0.0004

Data Index: 70134 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0302. Min Act: -0.0003

Data Index: 870671 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0307. Min Act: -0.0003

Data Index: 205874 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0324. Min Act: -0.0003

Data Index: 590710 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1003264 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1086739 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0305. Min Act: -0.0003

Data Index: 271087 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0290. Min Act: -0.0003

Data Index: 544219 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0298. Min Act: -0.0003

Data Index: 159357 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1316500 (C4 (Web Text))

Max Activating Token Index: 431