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

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

Neuron 3707 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.7078. Min Act: -0.0001

Data Index: 996855 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.7005. Min Act: -0.0000

Data Index: 274668 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.4983. Min Act: -0.0001

Data Index: 678599 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.2686. Min Act: -0.0001

Data Index: 411886 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.2084. Min Act: -0.0001

Data Index: 646883 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.2245. Min Act: -0.0001

Data Index: 474903 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.1686. Min Act: -0.0001

Data Index: 1079298 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1009270 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.1445. Min Act: -0.0001

Data Index: 634860 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1195923 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.1942. Min Act: -0.0001

Data Index: 619855 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.1682. Min Act: -0.0000

Data Index: 731769 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.1616. Min Act: -0.0001

Data Index: 515027 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.1131. Min Act: -0.0001

Data Index: 1057751 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.0968. Min Act: -0.0000

Data Index: 1211100 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1291203 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9471. Min Act: -0.0001

Data Index: 406370 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9369. Min Act: -0.0000

Data Index: 566421 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9251. Min Act: -0.0000

Data Index: 461863 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9569. Min Act: -0.0000

Data Index: 878981 (C4 (Web Text))

Max Activating Token Index: 821