Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2556 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0000

Data Index: 638855 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1542133 (Python Code)

Max Activating Token Index: 390

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0375. Min Act: -0.0000

Data Index: 71777 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0352. Min Act: -0.0000

Data Index: 658862 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0319. Min Act: -0.0000

Data Index: 322353 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1177824 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0319. Min Act: -0.0000

Data Index: 376217 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0329. Min Act: -0.0000

Data Index: 400717 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0326. Min Act: -0.0000

Data Index: 265161 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0312. Min Act: -0.0000

Data Index: 715784 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0322. Min Act: -0.0000

Data Index: 770980 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0306. Min Act: -0.0000

Data Index: 214571 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0312. Min Act: -0.0000

Data Index: 25977 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0320. Min Act: -0.0000

Data Index: 161307 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0294. Min Act: -0.0000

Data Index: 626388 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0278. Min Act: -0.0000

Data Index: 1398579 (Python Code)

Max Activating Token Index: 911

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0295. Min Act: -0.0000

Data Index: 211656 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1319119 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0295. Min Act: -0.0000

Data Index: 669137 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0278. Min Act: -0.0000

Data Index: 254777 (C4 (Web Text))

Max Activating Token Index: 509