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

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

Neuron 18 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0732. Min Act: -0.0000

Data Index: 816533 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0629. Min Act: -0.0001

Data Index: 363324 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0592. Min Act: -0.0001

Data Index: 736891 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0550. Min Act: -0.0001

Data Index: 74920 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1097618 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0556. Min Act: -0.0000

Data Index: 500533 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0560. Min Act: -0.0001

Data Index: 985539 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0533. Min Act: -0.0000

Data Index: 184795 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0537. Min Act: -0.0001

Data Index: 684254 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0526. Min Act: -0.0000

Data Index: 699195 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0559. Min Act: -0.0000

Data Index: 938113 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0538. Min Act: -0.0000

Data Index: 864765 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0522. Min Act: -0.0000

Data Index: 163303 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1136707 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0511. Min Act: -0.0000

Data Index: 837083 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0516. Min Act: -0.0000

Data Index: 505277 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0517. Min Act: -0.0001

Data Index: 392644 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0502. Min Act: -0.0000

Data Index: 496128 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0516. Min Act: -0.0000

Data Index: 218097 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0491. Min Act: -0.0000

Data Index: 1205469 (C4 (Web Text))

Max Activating Token Index: 700