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

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

Neuron 1280 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0001

Data Index: 96014 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0404. Min Act: -0.0001

Data Index: 688883 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0416. Min Act: -0.0001

Data Index: 242725 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0368. Min Act: -0.0001

Data Index: 264789 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0403. Min Act: -0.0001

Data Index: 881133 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0384. Min Act: -0.0001

Data Index: 86250 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1045519 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0369. Min Act: -0.0001

Data Index: 784970 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0377. Min Act: -0.0000

Data Index: 702545 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0362. Min Act: -0.0001

Data Index: 911333 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1251246 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0371. Min Act: -0.0001

Data Index: 605940 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0353. Min Act: -0.0001

Data Index: 711168 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0346. Min Act: -0.0001

Data Index: 839024 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1357719 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0351. Min Act: -0.0001

Data Index: 789738 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0349. Min Act: -0.0001

Data Index: 183755 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1041726 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0345. Min Act: -0.0001

Data Index: 736725 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0338. Min Act: -0.0001

Data Index: 537171 (C4 (Web Text))

Max Activating Token Index: 269