Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1627 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0965. Min Act: -0.0003

Data Index: 805073 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0888. Min Act: -0.0002

Data Index: 550380 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0839. Min Act: -0.0002

Data Index: 140185 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1120866 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0793. Min Act: -0.0003

Data Index: 381891 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0779. Min Act: -0.0004

Data Index: 878375 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0754. Min Act: -0.0003

Data Index: 652813 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0765. Min Act: -0.0003

Data Index: 368332 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1137196 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1261608 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0765. Min Act: -0.0003

Data Index: 681811 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1136482 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0780. Min Act: -0.0003

Data Index: 14018 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1119852 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0701. Min Act: -0.0002

Data Index: 968496 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0716. Min Act: -0.0003

Data Index: 731785 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0757. Min Act: -0.0003

Data Index: 811821 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1130608 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0702. Min Act: -0.0002

Data Index: 249045 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0697. Min Act: -0.0003

Data Index: 425780 (C4 (Web Text))

Max Activating Token Index: 503