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

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

Neuron 5500 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.1627. Min Act: -0.0000

Data Index: 1154477 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0658. Min Act: -0.0000

Data Index: 712200 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1250711 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0045. Min Act: -0.0000

Data Index: 619704 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9444. Min Act: 0.0000

Data Index: 1090157 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9313. Min Act: -0.0000

Data Index: 361692 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9202. Min Act: -0.0000

Data Index: 421567 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8586. Min Act: -0.0000

Data Index: 488201 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1025870 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9040. Min Act: -0.0000

Data Index: 430571 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8924. Min Act: -0.0000

Data Index: 788105 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1004491 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9363. Min Act: -0.0000

Data Index: 488691 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9324. Min Act: -0.0000

Data Index: 591183 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1004937 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8729. Min Act: -0.0000

Data Index: 186701 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1262423 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8682. Min Act: -0.0000

Data Index: 816736 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8326. Min Act: -0.0000

Data Index: 516300 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8282. Min Act: -0.0000

Data Index: 927703 (C4 (Web Text))

Max Activating Token Index: 214