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

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

Neuron 3597 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.1220. Min Act: -0.0000

Data Index: 300586 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8971. Min Act: -0.0000

Data Index: 679466 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8829. Min Act: -0.0000

Data Index: 170574 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8324. Min Act: -0.0000

Data Index: 446868 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8985. Min Act: -0.0000

Data Index: 759367 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8842. Min Act: -0.0000

Data Index: 146219 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1160329 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1081097 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7846. Min Act: -0.0000

Data Index: 536165 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7376. Min Act: -0.0000

Data Index: 324535 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7565. Min Act: -0.0000

Data Index: 244061 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7282. Min Act: -0.0000

Data Index: 97731 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7680. Min Act: -0.0000

Data Index: 235741 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7684. Min Act: -0.0000

Data Index: 535181 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7095. Min Act: -0.0000

Data Index: 343588 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7566. Min Act: -0.0000

Data Index: 192795 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7251. Min Act: -0.0000

Data Index: 871597 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1179724 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.6868. Min Act: -0.0000

Data Index: 213055 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7212. Min Act: -0.0000

Data Index: 517847 (C4 (Web Text))

Max Activating Token Index: 327