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

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

Neuron 102 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0002

Data Index: 394046 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0730. Min Act: -0.0002

Data Index: 753219 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0724. Min Act: -0.0002

Data Index: 962668 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0685. Min Act: -0.0002

Data Index: 683382 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0647. Min Act: -0.0002

Data Index: 457059 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0638. Min Act: -0.0002

Data Index: 433628 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1172646 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0606. Min Act: -0.0002

Data Index: 606160 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0620. Min Act: -0.0002

Data Index: 808140 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1109849 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1200166 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0609. Min Act: -0.0002

Data Index: 196962 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0629. Min Act: -0.0002

Data Index: 910694 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0554. Min Act: -0.0002

Data Index: 555821 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0614. Min Act: -0.0002

Data Index: 166887 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0603. Min Act: -0.0002

Data Index: 116293 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1209382 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0580. Min Act: -0.0002

Data Index: 200928 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0572. Min Act: -0.0002

Data Index: 468379 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0612. Min Act: -0.0002

Data Index: 70755 (C4 (Web Text))

Max Activating Token Index: 369