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

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

Neuron 4208 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: 2.4744. Min Range: -2.4744

Max Act: 2.4744. Min Act: -0.0000

Data Index: 702945 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.3763. Min Act: -0.0000

Data Index: 58020 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.7253. Min Act: -0.0000

Data Index: 971609 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6519. Min Act: -0.0001

Data Index: 259824 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6499. Min Act: -0.0001

Data Index: 605807 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.5150. Min Act: -0.0001

Data Index: 1155879 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.5256. Min Act: -0.0000

Data Index: 686021 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.4027. Min Act: -0.0000

Data Index: 463514 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6079. Min Act: -0.0000

Data Index: 376446 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6495. Min Act: -0.0000

Data Index: 960042 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.4528. Min Act: -0.0000

Data Index: 830415 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.4360. Min Act: -0.0001

Data Index: 986482 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.4399. Min Act: -0.0001

Data Index: 997224 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.2164. Min Act: -0.0001

Data Index: 159007 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.3814. Min Act: -0.0000

Data Index: 1392755 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.4226. Min Act: -0.0001

Data Index: 466297 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.3367. Min Act: -0.0001

Data Index: 529852 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.3328. Min Act: -0.0000

Data Index: 811338 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.4510. Min Act: -0.0000

Data Index: 1055401 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.2520. Min Act: -0.0000

Data Index: 623968 (C4 (Web Text))

Max Activating Token Index: 357