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

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

Neuron 3734 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.2099. Min Act: -0.0001

Data Index: 167288 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1925. Min Act: -0.0001

Data Index: 273774 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1788. Min Act: -0.0002

Data Index: 721303 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1063400 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1765. Min Act: -0.0001

Data Index: 802537 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1601. Min Act: -0.0001

Data Index: 497673 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1581. Min Act: -0.0001

Data Index: 885982 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1521. Min Act: -0.0002

Data Index: 450968 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1595. Min Act: -0.0002

Data Index: 1305550 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1533. Min Act: -0.0002

Data Index: 54294 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1566. Min Act: -0.0002

Data Index: 29937 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1458. Min Act: -0.0002

Data Index: 585823 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1543. Min Act: -0.0001

Data Index: 795248 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1444. Min Act: -0.0001

Data Index: 318632 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1465. Min Act: -0.0002

Data Index: 271906 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1405. Min Act: -0.0002

Data Index: 881751 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1434. Min Act: -0.0001

Data Index: 1116032 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1383. Min Act: -0.0001

Data Index: 914559 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1413. Min Act: -0.0002

Data Index: 149683 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.2099. Min Range: -0.2099

Max Act: 0.1475. Min Act: -0.0001

Data Index: 729763 (C4 (Web Text))

Max Activating Token Index: 209