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

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

Neuron 3079 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: 0.0635. Min Range: -0.0635

Max Act: 0.0630. Min Act: -0.0000

Data Index: 1340410 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0612. Min Act: -0.0000

Data Index: 112703 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0625. Min Act: -0.0001

Data Index: 231904 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0629. Min Act: -0.0000

Data Index: 964068 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1094106 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1218606 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0591. Min Act: -0.0001

Data Index: 175283 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0587. Min Act: -0.0000

Data Index: 985104 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0579. Min Act: -0.0000

Data Index: 453636 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1122552 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1148051 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0569. Min Act: -0.0001

Data Index: 793626 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0590. Min Act: -0.0000

Data Index: 990862 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1031823 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0563. Min Act: -0.0000

Data Index: 391556 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0538. Min Act: -0.0001

Data Index: 379491 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0581. Min Act: -0.0000

Data Index: 249439 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1165022 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0551. Min Act: -0.0000

Data Index: 959651 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1129558 (C4 (Web Text))

Max Activating Token Index: 773