Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 23 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0003

Data Index: 197380 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1324129 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0712. Min Act: -0.0003

Data Index: 321808 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0700. Min Act: -0.0003

Data Index: 877341 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1239672 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0725. Min Act: -0.0003

Data Index: 944983 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0678. Min Act: -0.0003

Data Index: 688345 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0683. Min Act: -0.0003

Data Index: 512129 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1312253 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1332813 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0630. Min Act: -0.0003

Data Index: 760486 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0640. Min Act: -0.0003

Data Index: 70347 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1205552 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0702. Min Act: -0.0003

Data Index: 652625 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0642. Min Act: -0.0003

Data Index: 212236 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0628. Min Act: -0.0003

Data Index: 860658 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0708. Min Act: -0.0003

Data Index: 108424 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0676. Min Act: -0.0003

Data Index: 422445 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0672. Min Act: -0.0003

Data Index: 499274 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1217142 (C4 (Web Text))

Max Activating Token Index: 491