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

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

Neuron 4485 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1047667 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0442. Min Act: -0.0002

Data Index: 151087 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0449. Min Act: -0.0002

Data Index: 342374 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0452. Min Act: -0.0002

Data Index: 723343 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0377. Min Act: -0.0003

Data Index: 521507 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0400. Min Act: -0.0002

Data Index: 169470 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0366. Min Act: -0.0002

Data Index: 118339 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0374. Min Act: -0.0002

Data Index: 999366 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0381. Min Act: -0.0002

Data Index: 678009 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1437792 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0377. Min Act: -0.0002

Data Index: 479645 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1593560 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0366. Min Act: -0.0002

Data Index: 913580 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0331. Min Act: -0.0002

Data Index: 41866 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0324. Min Act: -0.0002

Data Index: 469390 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0352. Min Act: -0.0002

Data Index: 400162 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0367. Min Act: -0.0002

Data Index: 880165 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1561246 (Python Code)

Max Activating Token Index: 377

Text #18

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0323. Min Act: -0.0002

Data Index: 23193 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1457468 (Python Code)

Max Activating Token Index: 193