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

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

Neuron 3612 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0003

Data Index: 71335 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0554. Min Act: -0.0003

Data Index: 329326 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0525. Min Act: -0.0003

Data Index: 548016 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1068936 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0496. Min Act: -0.0003

Data Index: 56611 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0461. Min Act: -0.0003

Data Index: 756504 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0475. Min Act: -0.0003

Data Index: 950275 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0453. Min Act: -0.0003

Data Index: 844627 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1184395 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0442. Min Act: -0.0003

Data Index: 186080 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0452. Min Act: -0.0003

Data Index: 448159 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0422. Min Act: -0.0003

Data Index: 303538 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0419. Min Act: -0.0003

Data Index: 881754 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0423. Min Act: -0.0003

Data Index: 255318 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1103176 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0429. Min Act: -0.0003

Data Index: 491019 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1202082 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1269507 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0422. Min Act: -0.0003

Data Index: 31712 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0409. Min Act: -0.0003

Data Index: 686069 (C4 (Web Text))

Max Activating Token Index: 459