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

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

Neuron 4538 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: 0.0436. Min Range: -0.0436

Max Act: 0.0403. Min Act: -0.0003

Data Index: 713776 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0418. Min Act: -0.0002

Data Index: 755226 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0436. Min Act: -0.0003

Data Index: 357826 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0413. Min Act: -0.0003

Data Index: 110963 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0391. Min Act: -0.0003

Data Index: 54808 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0371. Min Act: -0.0003

Data Index: 545858 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0377. Min Act: -0.0003

Data Index: 80438 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0383. Min Act: -0.0003

Data Index: 684841 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1132002 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1174461 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0346. Min Act: -0.0003

Data Index: 715848 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0345. Min Act: -0.0003

Data Index: 912779 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0351. Min Act: -0.0003

Data Index: 143458 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0337. Min Act: -0.0003

Data Index: 480961 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0337. Min Act: -0.0002

Data Index: 812067 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0331. Min Act: -0.0003

Data Index: 491109 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1030072 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0333. Min Act: -0.0003

Data Index: 114564 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0328. Min Act: -0.0003

Data Index: 687617 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0328. Min Act: -0.0002

Data Index: 703550 (C4 (Web Text))

Max Activating Token Index: 619