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

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

Neuron 2308 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: 0.0893. Min Range: -0.0893

Max Act: 0.0893. Min Act: -0.0001

Data Index: 768014 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0683. Min Act: -0.0001

Data Index: 414633 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0662. Min Act: -0.0001

Data Index: 427459 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0648. Min Act: -0.0001

Data Index: 290888 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0681. Min Act: -0.0001

Data Index: 522304 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0654. Min Act: -0.0001

Data Index: 837924 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0603. Min Act: -0.0001

Data Index: 843242 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0586. Min Act: -0.0001

Data Index: 25839 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0607. Min Act: -0.0001

Data Index: 941508 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0570. Min Act: -0.0001

Data Index: 254932 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0610. Min Act: -0.0001

Data Index: 890875 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1181848 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0595. Min Act: -0.0001

Data Index: 663611 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0547. Min Act: -0.0001

Data Index: 402858 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0521. Min Act: -0.0001

Data Index: 897318 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1348879 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0577. Min Act: -0.0001

Data Index: 76213 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0580. Min Act: -0.0001

Data Index: 134777 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1062412 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1276727 (C4 (Web Text))

Max Activating Token Index: 392