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

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

Neuron 83 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.4472. Min Act: -0.0001

Data Index: 839496 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.4768. Min Act: -0.0000

Data Index: 873080 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.3282. Min Act: -0.0000

Data Index: 623988 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.1455. Min Act: -0.0001

Data Index: 305444 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.1177. Min Act: -0.0000

Data Index: 165464 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.1311. Min Act: -0.0000

Data Index: 1297726 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.0118. Min Act: -0.0000

Data Index: 127008 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.1713. Min Act: -0.0000

Data Index: 1250463 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.0319. Min Act: -0.0001

Data Index: 654506 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.0211. Min Act: -0.0000

Data Index: 1315946 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.0317. Min Act: -0.0000

Data Index: 204733 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 3.4472. Min Range: -3.4472

Max Act: 1.9685. Min Act: -0.0000

Data Index: 487786 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.1677. Min Act: -0.0000

Data Index: 1127613 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 3.4472. Min Range: -3.4472

Max Act: 1.6355. Min Act: -0.0001

Data Index: 364752 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 3.4472. Min Range: -3.4472

Max Act: 1.8115. Min Act: -0.0000

Data Index: 436538 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 3.4472. Min Range: -3.4472

Max Act: 1.8133. Min Act: -0.0000

Data Index: 1213787 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 3.4472. Min Range: -3.4472

Max Act: 1.9955. Min Act: -0.0001

Data Index: 1352061 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 3.4472. Min Range: -3.4472

Max Act: 1.9279. Min Act: -0.0001

Data Index: 15528 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 3.4472. Min Range: -3.4472

Max Act: 2.0000. Min Act: -0.0001

Data Index: 1311507 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 3.4472. Min Range: -3.4472

Max Act: 1.9666. Min Act: -0.0000

Data Index: 587512 (C4 (Web Text))

Max Activating Token Index: 530