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

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

Neuron 921 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: 1.8167. Min Range: -1.8167

Max Act: 1.8167. Min Act: -0.0001

Data Index: 478298 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.3657. Min Act: -0.0001

Data Index: 596244 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.2827. Min Act: -0.0001

Data Index: 396535 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.2038. Min Act: -0.0001

Data Index: 996276 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.2816. Min Act: -0.0001

Data Index: 1028924 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1832. Min Act: -0.0001

Data Index: 465941 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.2110. Min Act: -0.0001

Data Index: 527982 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1319. Min Act: -0.0001

Data Index: 34689 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1916. Min Act: -0.0001

Data Index: 895737 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.2559. Min Act: -0.0001

Data Index: 86899 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1247. Min Act: -0.0001

Data Index: 597449 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1806. Min Act: -0.0001

Data Index: 173107 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1068. Min Act: -0.0001

Data Index: 117299 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1429. Min Act: -0.0001

Data Index: 102456 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.2001. Min Act: -0.0001

Data Index: 948550 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1600. Min Act: -0.0001

Data Index: 471970 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1633. Min Act: -0.0001

Data Index: 1281037 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.0885. Min Act: -0.0001

Data Index: 303509 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1078. Min Act: -0.0001

Data Index: 586189 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.1743. Min Act: -0.0001

Data Index: 720848 (C4 (Web Text))

Max Activating Token Index: 497