Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2023 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0001

Data Index: 1149811 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1688. Min Act: -0.0001

Data Index: 634992 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1600. Min Act: -0.0001

Data Index: 301456 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1661. Min Act: -0.0001

Data Index: 434543 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1482. Min Act: -0.0001

Data Index: 442919 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1449. Min Act: -0.0001

Data Index: 789615 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1503. Min Act: -0.0001

Data Index: 908230 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1332. Min Act: -0.0001

Data Index: 294992 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1477. Min Act: -0.0001

Data Index: 721072 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1406. Min Act: -0.0001

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1436. Min Act: -0.0001

Data Index: 282980 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1144595 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1362. Min Act: -0.0001

Data Index: 852714 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1251790 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1350849 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1368. Min Act: -0.0001

Data Index: 59727 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1172380 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1392. Min Act: -0.0001

Data Index: 82270 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1429. Min Act: -0.0001

Data Index: 995758 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1293. Min Act: -0.0001

Data Index: 1116972 (C4 (Web Text))

Max Activating Token Index: 215