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

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

Neuron 4738 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: 1.8738. Min Range: -1.8738

Max Act: 1.8738. Min Act: -0.0000

Data Index: 84914 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.5614. Min Act: -0.0000

Data Index: 718013 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.5814. Min Act: -0.0000

Data Index: 1164332 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.5919. Min Act: -0.0000

Data Index: 133380 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.7281. Min Act: -0.0000

Data Index: 286455 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.6074. Min Act: -0.0000

Data Index: 240762 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.5422. Min Act: -0.0001

Data Index: 681501 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.5306. Min Act: -0.0000

Data Index: 1246828 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.5140. Min Act: -0.0001

Data Index: 34960 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.4241. Min Act: -0.0000

Data Index: 231020 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.5882. Min Act: -0.0000

Data Index: 528241 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.3939. Min Act: -0.0000

Data Index: 322476 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.4223. Min Act: -0.0000

Data Index: 1238900 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.4026. Min Act: -0.0001

Data Index: 939916 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.4900. Min Act: -0.0001

Data Index: 506471 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.3797. Min Act: -0.0001

Data Index: 55538 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.3477. Min Act: -0.0000

Data Index: 516921 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.5381. Min Act: -0.0001

Data Index: 1115178 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.3563. Min Act: -0.0000

Data Index: 544618 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.4206. Min Act: -0.0000

Data Index: 1263935 (C4 (Web Text))

Max Activating Token Index: 572