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

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

Neuron 3561 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5573. Min Act: -0.0001

Data Index: 615784 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5660. Min Act: -0.0001

Data Index: 659635 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4954. Min Act: -0.0001

Data Index: 384880 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5175. Min Act: -0.0001

Data Index: 1254068 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4985. Min Act: -0.0002

Data Index: 954618 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4901. Min Act: -0.0002

Data Index: 312454 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4604. Min Act: -0.0001

Data Index: 1138649 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4660. Min Act: -0.0001

Data Index: 700506 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4828. Min Act: -0.0001

Data Index: 1238617 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4848. Min Act: -0.0001

Data Index: 903848 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4959. Min Act: -0.0001

Data Index: 1150623 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4599. Min Act: -0.0001

Data Index: 568407 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4751. Min Act: -0.0001

Data Index: 16372 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1108321 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4627. Min Act: -0.0002

Data Index: 1304823 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4763. Min Act: -0.0001

Data Index: 1351852 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4709. Min Act: -0.0001

Data Index: 45992 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4538. Min Act: -0.0002

Data Index: 1133808 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4290. Min Act: -0.0001

Data Index: 872256 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4391. Min Act: -0.0001

Data Index: 873984 (C4 (Web Text))

Max Activating Token Index: 96