Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2438 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.4593. Min Act: -0.0001

Data Index: 417624 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.4012. Min Act: -0.0001

Data Index: 853357 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2798. Min Act: -0.0001

Data Index: 751862 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2764. Min Act: -0.0001

Data Index: 106164 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1577. Min Act: -0.0001

Data Index: 1246007 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2623. Min Act: -0.0001

Data Index: 195409 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2813. Min Act: -0.0001

Data Index: 198941 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1607. Min Act: -0.0001

Data Index: 1111877 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 1.4593. Min Range: -1.4593

Max Act: 0.9573. Min Act: -0.0001

Data Index: 877038 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2480. Min Act: -0.0001

Data Index: 947169 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1273. Min Act: -0.0001

Data Index: 1073139 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 1.4593. Min Range: -1.4593

Max Act: 0.9844. Min Act: -0.0001

Data Index: 237642 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1121. Min Act: -0.0001

Data Index: 1324440 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.0910. Min Act: -0.0001

Data Index: 1337821 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1892. Min Act: -0.0001

Data Index: 35400 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1203. Min Act: -0.0001

Data Index: 297737 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1376. Min Act: -0.0001

Data Index: 566895 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1764. Min Act: -0.0001

Data Index: 811946 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1638. Min Act: -0.0001

Data Index: 517795 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.4593. Min Range: -1.4593

Max Act: 0.9132. Min Act: -0.0001

Data Index: 503580 (C4 (Web Text))

Max Activating Token Index: 860