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

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

Neuron 204 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: 0.1560. Min Range: -0.1560

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1316683 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1534. Min Act: -0.0001

Data Index: 873835 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1531. Min Act: -0.0001

Data Index: 282592 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1464. Min Act: -0.0001

Data Index: 298418 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1498. Min Act: -0.0001

Data Index: 729461 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1425. Min Act: -0.0001

Data Index: 43670 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1405. Min Act: -0.0001

Data Index: 390385 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1363. Min Act: -0.0001

Data Index: 1310578 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1306. Min Act: -0.0001

Data Index: 288149 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1353. Min Act: -0.0001

Data Index: 997232 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1083984 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1207. Min Act: -0.0001

Data Index: 543990 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1116076 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1234. Min Act: -0.0001

Data Index: 705839 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1321. Min Act: -0.0001

Data Index: 962619 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1222. Min Act: -0.0001

Data Index: 948720 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1230. Min Act: -0.0001

Data Index: 489263 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1223. Min Act: -0.0001

Data Index: 527636 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1270. Min Act: -0.0001

Data Index: 20406 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1249. Min Act: -0.0001

Data Index: 356829 (C4 (Web Text))

Max Activating Token Index: 762