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

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

Neuron 2260 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5238. Min Range: -1.5238

Max Act: 1.5238. Min Act: -0.0001

Data Index: 632630 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 1.5238. Min Range: -1.5238

Max Act: 1.3282. Min Act: -0.0001

Data Index: 227549 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.5238. Min Range: -1.5238

Max Act: 1.2031. Min Act: -0.0001

Data Index: 1290832 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 1.5238. Min Range: -1.5238

Max Act: 1.1256. Min Act: -0.0001

Data Index: 541306 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.5238. Min Range: -1.5238

Max Act: 1.1967. Min Act: -0.0001

Data Index: 875230 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.5238. Min Range: -1.5238

Max Act: 1.1508. Min Act: -0.0001

Data Index: 1088254 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 1.5238. Min Range: -1.5238

Max Act: 1.1302. Min Act: -0.0001

Data Index: 629111 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 1.5238. Min Range: -1.5238

Max Act: 1.0302. Min Act: -0.0001

Data Index: 326601 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 1.5238. Min Range: -1.5238

Max Act: 1.0013. Min Act: -0.0001

Data Index: 23337 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.9873. Min Act: -0.0001

Data Index: 416584 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.9315. Min Act: -0.0001

Data Index: 924307 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.9597. Min Act: -0.0001

Data Index: 229772 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.9126. Min Act: -0.0001

Data Index: 397343 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.9415. Min Act: -0.0001

Data Index: 948643 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.9031. Min Act: -0.0001

Data Index: 491767 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.9037. Min Act: -0.0001

Data Index: 687537 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.8931. Min Act: -0.0001

Data Index: 815876 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.8631. Min Act: -0.0001

Data Index: 43853 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.8696. Min Act: -0.0001

Data Index: 939633 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 1.5238. Min Range: -1.5238

Max Act: 0.9188. Min Act: -0.0001

Data Index: 128537 (C4 (Web Text))

Max Activating Token Index: 671