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

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

Neuron 281 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: 0.1722. Min Range: -0.1722

Max Act: 0.1722. Min Act: -0.0000

Data Index: 381084 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1623. Min Act: -0.0001

Data Index: 325735 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1705. Min Act: -0.0000

Data Index: 417837 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1629. Min Act: -0.0000

Data Index: 611035 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1478. Min Act: -0.0000

Data Index: 617393 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1484. Min Act: -0.0001

Data Index: 210875 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1511. Min Act: -0.0000

Data Index: 184179 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1459. Min Act: -0.0000

Data Index: 881714 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1485. Min Act: -0.0001

Data Index: 98821 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1074542 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1420. Min Act: -0.0000

Data Index: 941468 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1451. Min Act: -0.0001

Data Index: 217328 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1432. Min Act: -0.0001

Data Index: 910561 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1392. Min Act: -0.0001

Data Index: 727626 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1370. Min Act: -0.0000

Data Index: 314087 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1369. Min Act: -0.0001

Data Index: 270067 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1346. Min Act: -0.0000

Data Index: 958761 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1321. Min Act: -0.0000

Data Index: 588809 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1283. Min Act: -0.0001

Data Index: 791143 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1334. Min Act: -0.0000

Data Index: 996645 (C4 (Web Text))

Max Activating Token Index: 256