Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1917 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1730. Min Act: -0.0005

Data Index: 868894 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1644. Min Act: -0.0005

Data Index: 553218 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1610. Min Act: -0.0005

Data Index: 1112390 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1556. Min Act: -0.0005

Data Index: 183460 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1485. Min Act: -0.0005

Data Index: 898523 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1533. Min Act: -0.0005

Data Index: 235272 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1439. Min Act: -0.0005

Data Index: 163268 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1488. Min Act: -0.0005

Data Index: 400413 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1446. Min Act: -0.0005

Data Index: 853726 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1479. Min Act: -0.0005

Data Index: 1061838 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1445. Min Act: -0.0005

Data Index: 1300167 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1408. Min Act: -0.0005

Data Index: 31524 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1433. Min Act: -0.0005

Data Index: 740051 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1463. Min Act: -0.0005

Data Index: 968654 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1458. Min Act: -0.0005

Data Index: 890577 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1378. Min Act: -0.0005

Data Index: 1127009 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1380. Min Act: -0.0005

Data Index: 265359 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1362. Min Act: -0.0005

Data Index: 746716 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1325. Min Act: -0.0005

Data Index: 590922 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1268. Min Act: -0.0005

Data Index: 1178642 (C4 (Web Text))

Max Activating Token Index: 738