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

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

Neuron 2089 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.6269. Min Act: -0.0000

Data Index: 989002 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.6301. Min Act: -0.0000

Data Index: 468231 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5865. Min Act: -0.0000

Data Index: 931949 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5877. Min Act: -0.0001

Data Index: 1101921 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5800. Min Act: -0.0001

Data Index: 773671 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1026774 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5573. Min Act: -0.0000

Data Index: 49155 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5564. Min Act: -0.0000

Data Index: 646651 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5407. Min Act: -0.0000

Data Index: 81631 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5097. Min Act: -0.0000

Data Index: 674692 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5372. Min Act: -0.0001

Data Index: 749488 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4813. Min Act: -0.0000

Data Index: 649317 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4777. Min Act: -0.0000

Data Index: 479271 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4613. Min Act: -0.0001

Data Index: 324615 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4720. Min Act: -0.0001

Data Index: 709574 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4717. Min Act: -0.0000

Data Index: 737296 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4635. Min Act: -0.0001

Data Index: 485639 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4564. Min Act: -0.0001

Data Index: 1129775 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4454. Min Act: -0.0000

Data Index: 36111 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4449. Min Act: -0.0000

Data Index: 15373 (C4 (Web Text))

Max Activating Token Index: 909