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

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

Neuron 4220 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: 1.4219. Min Range: -1.4219

Max Act: 1.3224. Min Act: -0.0001

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.3160. Min Act: -0.0001

Data Index: 353770 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.3524. Min Act: -0.0001

Data Index: 747708 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1659. Min Act: -0.0001

Data Index: 160021 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.2713. Min Act: -0.0001

Data Index: 658717 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.2729. Min Act: -0.0001

Data Index: 83390 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.2517. Min Act: -0.0001

Data Index: 36772 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.3221. Min Act: -0.0001

Data Index: 399796 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.2216. Min Act: -0.0001

Data Index: 889521 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.4219. Min Act: -0.0001

Data Index: 1047523 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1856. Min Act: -0.0001

Data Index: 729834 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1826. Min Act: -0.0001

Data Index: 43218 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.0978. Min Act: -0.0001

Data Index: 838045 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.0155. Min Act: -0.0001

Data Index: 607873 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1143. Min Act: -0.0001

Data Index: 533750 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1708. Min Act: -0.0001

Data Index: 1240009 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1291. Min Act: -0.0001

Data Index: 1878 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1244. Min Act: -0.0001

Data Index: 1234598 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.0483. Min Act: -0.0001

Data Index: 678986 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1661. Min Act: -0.0001

Data Index: 121506 (C4 (Web Text))

Max Activating Token Index: 363