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

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

Neuron 1155 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8652. Min Act: -0.0001

Data Index: 777575 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.9604. Min Act: -0.0001

Data Index: 1344844 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8409. Min Act: -0.0001

Data Index: 304856 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8968. Min Act: -0.0001

Data Index: 1200131 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.9312. Min Act: -0.0001

Data Index: 1001445 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6807. Min Act: -0.0001

Data Index: 1151258 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8507. Min Act: -0.0001

Data Index: 311307 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6864. Min Act: -0.0001

Data Index: 1278432 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.7614. Min Act: -0.0001

Data Index: 481928 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.7281. Min Act: -0.0001

Data Index: 927630 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6438. Min Act: -0.0001

Data Index: 719485 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6653. Min Act: -0.0001

Data Index: 1326409 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.5754. Min Act: -0.0001

Data Index: 1324394 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.5765. Min Act: -0.0001

Data Index: 1003712 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.4638. Min Act: -0.0001

Data Index: 187967 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.5289. Min Act: -0.0001

Data Index: 163971 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6087. Min Act: -0.0001

Data Index: 1331348 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6671. Min Act: -0.0001

Data Index: 461388 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.6488. Min Act: -0.0001

Data Index: 862430 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.4791. Min Act: -0.0001

Data Index: 1226965 (C4 (Web Text))

Max Activating Token Index: 15