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

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

Neuron 2354 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1699. Min Act: -0.0001

Data Index: 338798 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1681. Min Act: -0.0001

Data Index: 927580 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1500. Min Act: -0.0001

Data Index: 742493 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1599. Min Act: -0.0001

Data Index: 773364 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1446. Min Act: -0.0001

Data Index: 767234 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1423. Min Act: -0.0001

Data Index: 303196 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1534. Min Act: -0.0001

Data Index: 512815 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1459. Min Act: -0.0001

Data Index: 156012 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1419. Min Act: -0.0001

Data Index: 521968 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1109012 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1034609 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1383. Min Act: -0.0001

Data Index: 918399 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1328. Min Act: -0.0001

Data Index: 220767 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1160386 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1377. Min Act: -0.0001

Data Index: 308174 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1270. Min Act: -0.0001

Data Index: 939561 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1281. Min Act: -0.0001

Data Index: 92192 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1279. Min Act: -0.0001

Data Index: 748276 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1301. Min Act: -0.0001

Data Index: 542332 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1035774 (C4 (Web Text))

Max Activating Token Index: 710