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

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

Neuron 795 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.3432. Min Act: -0.0000

Data Index: 1605320 (Python Code)

Max Activating Token Index: 703

Text #1

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1481. Min Act: -0.0000

Data Index: 495213 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1604. Min Act: -0.0000

Data Index: 291428 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1170992 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1530. Min Act: -0.0000

Data Index: 960431 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1305. Min Act: -0.0000

Data Index: 454964 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0507. Min Act: -0.0000

Data Index: 734085 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1805. Min Act: -0.0000

Data Index: 623591 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1540. Min Act: -0.0000

Data Index: 493817 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0712. Min Act: -0.0000

Data Index: 872164 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1209278 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0966. Min Act: -0.0000

Data Index: 811097 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0843. Min Act: -0.0000

Data Index: 778454 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0892. Min Act: -0.0000

Data Index: 129182 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1430. Min Act: -0.0000

Data Index: 493698 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1233079 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0412. Min Act: -0.0000

Data Index: 387437 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9526. Min Act: -0.0000

Data Index: 498875 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9176. Min Act: -0.0000

Data Index: 38752 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9358. Min Act: -0.0000

Data Index: 288777 (C4 (Web Text))

Max Activating Token Index: 170