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

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

Neuron 4153 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3609. Min Act: -0.0001

Data Index: 135784 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1183825 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3414. Min Act: -0.0001

Data Index: 913854 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3243. Min Act: -0.0001

Data Index: 944225 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3004. Min Act: -0.0001

Data Index: 141107 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3157. Min Act: -0.0001

Data Index: 1247524 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3134. Min Act: -0.0001

Data Index: 1282201 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3002. Min Act: -0.0001

Data Index: 805279 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2981. Min Act: -0.0001

Data Index: 972378 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2863. Min Act: -0.0001

Data Index: 551576 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2883. Min Act: -0.0001

Data Index: 181753 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2809. Min Act: -0.0001

Data Index: 798017 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2682. Min Act: -0.0001

Data Index: 29304 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2745. Min Act: -0.0001

Data Index: 773103 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2728. Min Act: -0.0001

Data Index: 979529 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2803. Min Act: -0.0001

Data Index: 695357 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2718. Min Act: -0.0001

Data Index: 919600 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1065924 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2753. Min Act: -0.0001

Data Index: 525068 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2756. Min Act: -0.0001

Data Index: 250970 (C4 (Web Text))

Max Activating Token Index: 651