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

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

Neuron 1021 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1195898 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1041723 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1142814 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1533662 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0716. Min Act: -0.0001

Data Index: 79741 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0781. Min Act: -0.0001

Data Index: 631391 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0723. Min Act: -0.0001

Data Index: 76806 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0712. Min Act: -0.0001

Data Index: 438278 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1334616 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1521603 (Python Code)

Max Activating Token Index: 167

Text #10

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0731. Min Act: -0.0001

Data Index: 535220 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0700. Min Act: -0.0001

Data Index: 194337 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1346375 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0703. Min Act: -0.0001

Data Index: 341963 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0677. Min Act: -0.0001

Data Index: 462002 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0749. Min Act: -0.0001

Data Index: 246305 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0670. Min Act: -0.0001

Data Index: 417045 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1033958 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0666. Min Act: -0.0001

Data Index: 146327 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1380103 (Python Code)

Max Activating Token Index: 25