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

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

Neuron 3150 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1253626 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0683. Min Act: -0.0001

Data Index: 910812 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0564. Min Act: -0.0001

Data Index: 196924 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0657. Min Act: -0.0001

Data Index: 1157924 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1132278 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0583. Min Act: -0.0000

Data Index: 1285056 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1433446 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0555. Min Act: -0.0001

Data Index: 457093 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0552. Min Act: -0.0001

Data Index: 623696 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1240364 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0581. Min Act: -0.0001

Data Index: 121693 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0527. Min Act: -0.0001

Data Index: 515519 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0540. Min Act: -0.0000

Data Index: 406299 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0575. Min Act: -0.0001

Data Index: 358464 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1016210 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0552. Min Act: -0.0001

Data Index: 266013 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0557. Min Act: -0.0001

Data Index: 926391 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1212224 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1205272 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1081273 (C4 (Web Text))

Max Activating Token Index: 984