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

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

Neuron 3450 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.7021. Min Act: -0.0000

Data Index: 735024 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.6266. Min Act: -0.0000

Data Index: 766299 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5651. Min Act: -0.0000

Data Index: 299051 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5921. Min Act: -0.0000

Data Index: 333139 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1315568 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5690. Min Act: -0.0000

Data Index: 630225 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5788. Min Act: -0.0000

Data Index: 924604 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1283187 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1232323 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5354. Min Act: -0.0000

Data Index: 709759 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5655. Min Act: -0.0000

Data Index: 362827 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1211425 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5574. Min Act: -0.0000

Data Index: 772747 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5273. Min Act: -0.0000

Data Index: 356386 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5347. Min Act: -0.0000

Data Index: 836895 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5378. Min Act: -0.0000

Data Index: 161015 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5481. Min Act: -0.0000

Data Index: 634289 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5287. Min Act: -0.0000

Data Index: 925317 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5286. Min Act: -0.0000

Data Index: 45601 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.7021. Min Range: -0.7021

Max Act: 0.5127. Min Act: -0.0000

Data Index: 211938 (C4 (Web Text))

Max Activating Token Index: 272