Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 42 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7448. Min Act: -0.0001

Data Index: 17659 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.8046. Min Act: -0.0001

Data Index: 292860 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.6367. Min Act: -0.0001

Data Index: 63563 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.8742. Min Act: -0.0001

Data Index: 1054536 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.5414. Min Act: -0.0001

Data Index: 135409 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.4519. Min Act: -0.0000

Data Index: 871256 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.5327. Min Act: -0.0001

Data Index: 897996 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.3147. Min Act: -0.0001

Data Index: 325001 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.1559. Min Act: -0.0000

Data Index: 722496 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.2486. Min Act: -0.0001

Data Index: 1211640 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.2053. Min Act: -0.0001

Data Index: 772172 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.3225. Min Act: -0.0001

Data Index: 380294 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.1718. Min Act: -0.0001

Data Index: 218610 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.0139. Min Act: -0.0001

Data Index: 1020436 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.2574. Min Act: -0.0001

Data Index: 1240529 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.0617. Min Act: -0.0000

Data Index: 1351048 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.0378. Min Act: -0.0001

Data Index: 803863 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.0316. Min Act: -0.0001

Data Index: 593003 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.0185. Min Act: -0.0001

Data Index: 44648 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.0210. Min Act: -0.0001

Data Index: 744102 (C4 (Web Text))

Max Activating Token Index: 529