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

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

Neuron 1264 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0002

Data Index: 987650 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0648. Min Act: -0.0002

Data Index: 331781 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1173760 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0605. Min Act: -0.0002

Data Index: 759690 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0575. Min Act: -0.0003

Data Index: 524383 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0592. Min Act: -0.0002

Data Index: 182604 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0599. Min Act: -0.0002

Data Index: 926907 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0577. Min Act: -0.0002

Data Index: 880952 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0559. Min Act: -0.0002

Data Index: 994860 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1053045 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1069604 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0503. Min Act: -0.0002

Data Index: 886032 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1345577 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1195575 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0413. Min Act: -0.0002

Data Index: 945429 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0429. Min Act: -0.0003

Data Index: 371199 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1019007 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0407. Min Act: -0.0003

Data Index: 300182 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0418. Min Act: -0.0003

Data Index: 402860 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0408. Min Act: -0.0002

Data Index: 350358 (C4 (Web Text))

Max Activating Token Index: 563