Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5115 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1440. Min Act: -0.0000

Data Index: 910123 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1482. Min Act: -0.0001

Data Index: 452951 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1299. Min Act: -0.0001

Data Index: 813891 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1399. Min Act: -0.0001

Data Index: 380398 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1416. Min Act: -0.0001

Data Index: 954690 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1376. Min Act: -0.0001

Data Index: 912045 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1018147 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1244. Min Act: -0.0000

Data Index: 123437 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1588181 (Python Code)

Max Activating Token Index: 337

Text #9

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1273. Min Act: -0.0000

Data Index: 104908 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1134. Min Act: -0.0000

Data Index: 888741 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1158. Min Act: -0.0001

Data Index: 222161 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1075186 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1181. Min Act: -0.0001

Data Index: 636001 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1130800 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1222. Min Act: -0.0001

Data Index: 527742 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1148119 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1020. Min Act: -0.0001

Data Index: 451848 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1080. Min Act: -0.0001

Data Index: 350873 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1357543 (C4 (Web Text))

Max Activating Token Index: 943