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

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

Neuron 3200 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0002

Data Index: 367229 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0651. Min Act: -0.0002

Data Index: 992243 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0641. Min Act: -0.0002

Data Index: 697097 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0639. Min Act: -0.0002

Data Index: 754127 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0629. Min Act: -0.0002

Data Index: 676492 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1340331 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0639. Min Act: -0.0002

Data Index: 981116 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0634. Min Act: -0.0002

Data Index: 142826 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1048306 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1284992 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1279346 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1120128 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0556. Min Act: -0.0002

Data Index: 777242 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0573. Min Act: -0.0002

Data Index: 466491 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0597. Min Act: -0.0002

Data Index: 85686 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0549. Min Act: -0.0002

Data Index: 123529 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0570. Min Act: -0.0002

Data Index: 782845 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0587. Min Act: -0.0002

Data Index: 259603 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0566. Min Act: -0.0002

Data Index: 210156 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0564. Min Act: -0.0002

Data Index: 488307 (C4 (Web Text))

Max Activating Token Index: 128