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

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

Neuron 529 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.1470. Min Act: -0.0000

Data Index: 930758 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.0135. Min Act: 0.0000

Data Index: 1040312 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.0739. Min Act: 0.0000

Data Index: 970465 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.1242. Min Act: 0.0000

Data Index: 235784 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1105069 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.0446. Min Act: 0.0000

Data Index: 932484 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.0260. Min Act: -0.0000

Data Index: 41566 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1238633 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.0214. Min Act: -0.0000

Data Index: 936622 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9770. Min Act: -0.0000

Data Index: 611210 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9267. Min Act: 0.0002

Data Index: 1347577 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1348982 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9450. Min Act: 0.0001

Data Index: 1109950 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8745. Min Act: -0.0000

Data Index: 145575 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8928. Min Act: -0.0000

Data Index: 36193 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1175808 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8496. Min Act: 0.0000

Data Index: 466107 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8246. Min Act: -0.0000

Data Index: 856495 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1252357 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8420. Min Act: 0.0000

Data Index: 753881 (C4 (Web Text))

Max Activating Token Index: 392