Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3101 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0635. Min Act: -0.0000

Data Index: 477203 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0529. Min Act: -0.0000

Data Index: 983410 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0548. Min Act: -0.0000

Data Index: 943497 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0478. Min Act: -0.0000

Data Index: 915036 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0539. Min Act: -0.0000

Data Index: 695567 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0507. Min Act: -0.0000

Data Index: 18566 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0484. Min Act: -0.0000

Data Index: 96223 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0468. Min Act: -0.0000

Data Index: 104797 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0474. Min Act: -0.0000

Data Index: 420558 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0464. Min Act: -0.0000

Data Index: 1195674 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0462. Min Act: -0.0000

Data Index: 2749 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1110639 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0509. Min Act: -0.0000

Data Index: 594932 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0421. Min Act: -0.0000

Data Index: 247109 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0467. Min Act: -0.0000

Data Index: 195696 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0479. Min Act: -0.0000

Data Index: 643538 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0428. Min Act: -0.0000

Data Index: 360015 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0442. Min Act: -0.0000

Data Index: 123739 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0440. Min Act: -0.0000

Data Index: 1333505 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0427. Min Act: -0.0000

Data Index: 416725 (C4 (Web Text))

Max Activating Token Index: 683