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

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

Neuron 458 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1985. Min Act: -0.0001

Data Index: 433398 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1213783 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1460. Min Act: -0.0001

Data Index: 581543 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1496. Min Act: -0.0001

Data Index: 784590 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1276661 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1482. Min Act: -0.0001

Data Index: 824199 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1398. Min Act: -0.0001

Data Index: 556142 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1352. Min Act: -0.0001

Data Index: 545205 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1441. Min Act: -0.0001

Data Index: 431011 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1434. Min Act: -0.0001

Data Index: 171179 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1222751 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1426. Min Act: -0.0001

Data Index: 952907 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1379. Min Act: -0.0001

Data Index: 416262 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1374. Min Act: -0.0001

Data Index: 935284 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1367. Min Act: -0.0001

Data Index: 1196530 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1296. Min Act: -0.0001

Data Index: 618435 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1339. Min Act: -0.0001

Data Index: 167591 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1350. Min Act: -0.0001

Data Index: 757355 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1278. Min Act: -0.0001

Data Index: 260429 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1303. Min Act: -0.0001

Data Index: 451549 (C4 (Web Text))

Max Activating Token Index: 700