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

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

Neuron 749 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.9342. Min Act: -0.0000

Data Index: 1226485 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.6665. Min Act: -0.0000

Data Index: 223084 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1083691 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.1977. Min Act: -0.0000

Data Index: 245547 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.0736. Min Act: -0.0000

Data Index: 424764 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 1.9342. Min Range: -1.9342

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1137334 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.0461. Min Act: -0.0000

Data Index: 585000 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.0649. Min Act: -0.0000

Data Index: 159607 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.0548. Min Act: -0.0000

Data Index: 687889 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1276546 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1318186 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.9342. Min Range: -1.9342

Max Act: 0.9658. Min Act: -0.0000

Data Index: 35673 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1074195 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 1.9342. Min Range: -1.9342

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1131553 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.0363. Min Act: -0.0000

Data Index: 692574 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 1.9342. Min Range: -1.9342

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1025588 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 1.9342. Min Range: -1.9342

Max Act: 0.9221. Min Act: -0.0000

Data Index: 628139 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 1.9342. Min Range: -1.9342

Max Act: 0.9526. Min Act: -0.0000

Data Index: 128200 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.9342. Min Range: -1.9342

Max Act: 0.9537. Min Act: -0.0000

Data Index: 249272 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.9342. Min Range: -1.9342

Max Act: 0.9261. Min Act: -0.0000

Data Index: 801378 (C4 (Web Text))

Max Activating Token Index: 499