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

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

Neuron 3541 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2296. Min Act: -0.0002

Data Index: 241753 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1755. Min Act: -0.0002

Data Index: 385463 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1623. Min Act: -0.0002

Data Index: 957716 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1728. Min Act: -0.0002

Data Index: 740110 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1644. Min Act: -0.0002

Data Index: 400529 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1636. Min Act: -0.0002

Data Index: 65496 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1540. Min Act: -0.0002

Data Index: 1148191 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1521. Min Act: -0.0002

Data Index: 723668 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1457. Min Act: -0.0002

Data Index: 592344 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1414. Min Act: -0.0002

Data Index: 685693 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1451. Min Act: -0.0002

Data Index: 640225 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1455. Min Act: -0.0002

Data Index: 882920 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1469. Min Act: -0.0002

Data Index: 611835 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1373. Min Act: -0.0002

Data Index: 122727 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1409. Min Act: -0.0002

Data Index: 1007867 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1392. Min Act: -0.0002

Data Index: 546217 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1337. Min Act: -0.0002

Data Index: 1196539 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1298. Min Act: -0.0002

Data Index: 1044190 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1381. Min Act: -0.0002

Data Index: 290711 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1280. Min Act: -0.0002

Data Index: 242717 (C4 (Web Text))

Max Activating Token Index: 282