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

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

Neuron 915 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0531. Min Range: -1.0531

Max Act: 1.0531. Min Act: -0.0001

Data Index: 192853 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.9808. Min Act: -0.0001

Data Index: 656142 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 1.0531. Min Range: -1.0531

Max Act: 1.0300. Min Act: -0.0001

Data Index: 885602 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.9332. Min Act: -0.0001

Data Index: 147173 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.9468. Min Act: -0.0001

Data Index: 331180 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.9610. Min Act: -0.0001

Data Index: 1279326 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.0531. Min Range: -1.0531

Max Act: 1.0177. Min Act: -0.0001

Data Index: 893663 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.9428. Min Act: -0.0001

Data Index: 1359283 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8796. Min Act: -0.0001

Data Index: 474221 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.9064. Min Act: -0.0001

Data Index: 212510 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8912. Min Act: -0.0001

Data Index: 1251505 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8594. Min Act: -0.0001

Data Index: 129761 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8811. Min Act: -0.0001

Data Index: 868666 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.9333. Min Act: -0.0001

Data Index: 791173 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8527. Min Act: -0.0001

Data Index: 844045 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8642. Min Act: -0.0001

Data Index: 106158 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8722. Min Act: -0.0001

Data Index: 1183878 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8725. Min Act: -0.0001

Data Index: 387461 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8676. Min Act: -0.0001

Data Index: 420203 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.0531. Min Range: -1.0531

Max Act: 0.8891. Min Act: -0.0001

Data Index: 1127940 (C4 (Web Text))

Max Activating Token Index: 512