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

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

Neuron 3302 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: 0.0476. Min Range: -0.0476

Max Act: 0.0469. Min Act: -0.0003

Data Index: 692488 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0003

Data Index: 379574 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0430. Min Act: -0.0003

Data Index: 9690 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1251969 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0386. Min Act: -0.0003

Data Index: 434990 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0401. Min Act: -0.0003

Data Index: 778688 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0372. Min Act: -0.0003

Data Index: 75227 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0391. Min Act: -0.0003

Data Index: 174009 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0389. Min Act: -0.0003

Data Index: 132211 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0367. Min Act: -0.0003

Data Index: 951032 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0377. Min Act: -0.0003

Data Index: 646938 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0374. Min Act: -0.0003

Data Index: 126505 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0374. Min Act: -0.0003

Data Index: 981695 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1009085 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0369. Min Act: -0.0003

Data Index: 236115 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0373. Min Act: -0.0003

Data Index: 858351 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1010291 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0332. Min Act: -0.0003

Data Index: 854487 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0369. Min Act: -0.0003

Data Index: 526418 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0374. Min Act: -0.0003

Data Index: 562979 (C4 (Web Text))

Max Activating Token Index: 205