Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3286 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0612. Min Act: -0.0001

Data Index: 257577 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0620. Min Act: -0.0001

Data Index: 301967 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0594. Min Act: -0.0001

Data Index: 668835 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0609. Min Act: -0.0001

Data Index: 915309 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0593. Min Act: -0.0001

Data Index: 781366 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0593. Min Act: -0.0001

Data Index: 232605 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1081605 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0588. Min Act: -0.0001

Data Index: 516715 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1240198 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0597. Min Act: -0.0001

Data Index: 109561 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0582. Min Act: -0.0001

Data Index: 854087 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0581. Min Act: -0.0001

Data Index: 866927 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0573. Min Act: -0.0001

Data Index: 690632 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0589. Min Act: -0.0001

Data Index: 227771 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0570. Min Act: -0.0001

Data Index: 942037 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1104765 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1205407 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0575. Min Act: -0.0001

Data Index: 223628 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1183297 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0583. Min Act: -0.0001

Data Index: 217868 (C4 (Web Text))

Max Activating Token Index: 237