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

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

Neuron 347 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: 0.0897. Min Range: -0.0897

Max Act: 0.0897. Min Act: -0.0003

Data Index: 336217 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0830. Min Act: -0.0004

Data Index: 1081806 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0827. Min Act: -0.0002

Data Index: 254414 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0788. Min Act: -0.0003

Data Index: 1135221 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1337956 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0763. Min Act: -0.0003

Data Index: 729828 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0770. Min Act: -0.0003

Data Index: 1153235 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0743. Min Act: -0.0003

Data Index: 327677 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0784. Min Act: -0.0004

Data Index: 875980 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0768. Min Act: -0.0003

Data Index: 481691 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0759. Min Act: -0.0003

Data Index: 1204545 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0763. Min Act: -0.0003

Data Index: 933982 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0787. Min Act: -0.0003

Data Index: 925517 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0778. Min Act: -0.0003

Data Index: 1090039 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0758. Min Act: -0.0003

Data Index: 660109 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0755. Min Act: -0.0003

Data Index: 341319 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0691. Min Act: -0.0003

Data Index: 316083 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0718. Min Act: -0.0003

Data Index: 865885 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0735. Min Act: -0.0003

Data Index: 966270 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0742. Min Act: -0.0003

Data Index: 1004685 (C4 (Web Text))

Max Activating Token Index: 808