Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 166 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2311. Min Act: -0.0002

Data Index: 874230 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1838. Min Act: -0.0002

Data Index: 1272318 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1728. Min Act: -0.0002

Data Index: 836125 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1754. Min Act: -0.0002

Data Index: 958438 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1707. Min Act: -0.0002

Data Index: 838016 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1806. Min Act: -0.0002

Data Index: 1147964 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1693. Min Act: -0.0002

Data Index: 1342800 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1754. Min Act: -0.0002

Data Index: 887194 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1640. Min Act: -0.0002

Data Index: 753004 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1526. Min Act: -0.0002

Data Index: 1309076 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1692. Min Act: -0.0002

Data Index: 575487 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1316. Min Act: -0.0002

Data Index: 1074075 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1573. Min Act: -0.0002

Data Index: 9920 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1700. Min Act: -0.0002

Data Index: 1006115 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1536. Min Act: -0.0002

Data Index: 864577 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1500. Min Act: -0.0002

Data Index: 430809 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1733. Min Act: -0.0002

Data Index: 316266 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1645. Min Act: -0.0002

Data Index: 1024469 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1582. Min Act: -0.0002

Data Index: 191245 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1628. Min Act: -0.0002

Data Index: 606972 (C4 (Web Text))

Max Activating Token Index: 717