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

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

Neuron 31 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1604. Min Act: -0.0001

Data Index: 31219 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1695. Min Act: -0.0001

Data Index: 688017 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1706. Min Act: -0.0001

Data Index: 221202 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1482. Min Act: -0.0001

Data Index: 783384 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1434. Min Act: -0.0001

Data Index: 595884 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1614. Min Act: -0.0001

Data Index: 502563 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1120680 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1335. Min Act: -0.0001

Data Index: 140121 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1392. Min Act: -0.0001

Data Index: 7598 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1610 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1310. Min Act: -0.0001

Data Index: 343423 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1349. Min Act: -0.0001

Data Index: 515423 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1277. Min Act: -0.0001

Data Index: 38215 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1412. Min Act: -0.0001

Data Index: 461511 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1374. Min Act: -0.0001

Data Index: 927015 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1374. Min Act: -0.0001

Data Index: 295884 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1332. Min Act: -0.0001

Data Index: 224601 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1266. Min Act: -0.0001

Data Index: 858165 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1139142 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1285. Min Act: -0.0001

Data Index: 439167 (C4 (Web Text))

Max Activating Token Index: 448