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

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

Neuron 2450 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.5497. Min Act: -0.0001

Data Index: 319421 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1317864 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.1696. Min Act: -0.0001

Data Index: 763247 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.0926. Min Act: -0.0001

Data Index: 929537 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1353546 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9232. Min Act: -0.0001

Data Index: 259085 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8778. Min Act: -0.0001

Data Index: 627081 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9329. Min Act: -0.0001

Data Index: 1302769 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9441. Min Act: -0.0001

Data Index: 162101 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9768. Min Act: -0.0000

Data Index: 222253 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8922. Min Act: -0.0001

Data Index: 656137 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1162783 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8613. Min Act: -0.0001

Data Index: 123466 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1296236 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8442. Min Act: -0.0001

Data Index: 1287724 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8256. Min Act: -0.0001

Data Index: 233877 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8850. Min Act: -0.0000

Data Index: 662719 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.7466. Min Act: -0.0001

Data Index: 2449 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.7121. Min Act: -0.0000

Data Index: 527808 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.7773. Min Act: -0.0001

Data Index: 1296266 (C4 (Web Text))

Max Activating Token Index: 1000