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

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

Neuron 209 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3701. Min Act: -0.0001

Data Index: 50433 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3319. Min Act: -0.0000

Data Index: 53223 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3183. Min Act: -0.0000

Data Index: 879363 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3322. Min Act: -0.0000

Data Index: 172326 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2987. Min Act: -0.0001

Data Index: 372194 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2926. Min Act: -0.0001

Data Index: 774573 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2686. Min Act: -0.0000

Data Index: 233006 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2542. Min Act: -0.0000

Data Index: 37887 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2473. Min Act: -0.0000

Data Index: 683151 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2448. Min Act: -0.0000

Data Index: 341981 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1075469 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2336. Min Act: -0.0000

Data Index: 477015 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2344. Min Act: -0.0000

Data Index: 459682 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1226885 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2168. Min Act: -0.0001

Data Index: 299692 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2224. Min Act: -0.0000

Data Index: 58595 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2203. Min Act: -0.0000

Data Index: 576424 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.1878. Min Act: -0.0000

Data Index: 9190 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2206. Min Act: -0.0000

Data Index: 778321 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2179. Min Act: -0.0000

Data Index: 387751 (C4 (Web Text))

Max Activating Token Index: 622