Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5170 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.4243. Min Act: -0.0000

Data Index: 376906 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1330955 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3965. Min Act: -0.0000

Data Index: 770033 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1138559 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3625. Min Act: -0.0000

Data Index: 37805 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3805. Min Act: -0.0000

Data Index: 7664 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3621. Min Act: -0.0000

Data Index: 989762 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3360. Min Act: -0.0000

Data Index: 17976 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3437. Min Act: -0.0000

Data Index: 658724 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1094439 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1303601 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3608. Min Act: -0.0000

Data Index: 924117 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3260. Min Act: -0.0000

Data Index: 918251 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3470. Min Act: -0.0000

Data Index: 600643 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3589. Min Act: -0.0000

Data Index: 279653 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1294436 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3485. Min Act: -0.0000

Data Index: 579386 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3382. Min Act: -0.0000

Data Index: 315498 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3158. Min Act: -0.0000

Data Index: 114078 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3558. Min Act: -0.0000

Data Index: 931423 (C4 (Web Text))

Max Activating Token Index: 27