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

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

Neuron 2424 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: 1.5857. Min Range: -1.5857

Max Act: 1.5857. Min Act: -0.0000

Data Index: 208088 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 1.5857. Min Range: -1.5857

Max Act: 1.1835. Min Act: -0.0000

Data Index: 686802 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.5857. Min Range: -1.5857

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1112165 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.5857. Min Range: -1.5857

Max Act: 1.1416. Min Act: -0.0000

Data Index: 206012 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 1.5857. Min Range: -1.5857

Max Act: 1.1823. Min Act: -0.0000

Data Index: 76849 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 1.5857. Min Range: -1.5857

Max Act: 1.0824. Min Act: -0.0000

Data Index: 223697 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.9563. Min Act: -0.0000

Data Index: 551866 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.9221. Min Act: -0.0000

Data Index: 846172 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.5857. Min Range: -1.5857

Max Act: 1.0200. Min Act: -0.0000

Data Index: 29239 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1247611 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 1.5857. Min Range: -1.5857

Max Act: 1.0026. Min Act: -0.0000

Data Index: 625618 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.8869. Min Act: -0.0000

Data Index: 439930 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1072330 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.8423. Min Act: -0.0000

Data Index: 140139 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.8849. Min Act: -0.0000

Data Index: 385328 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.8321. Min Act: -0.0000

Data Index: 809145 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.9378. Min Act: -0.0000

Data Index: 833295 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1226388 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.8063. Min Act: -0.0000

Data Index: 103090 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 1.5857. Min Range: -1.5857

Max Act: 0.8490. Min Act: -0.0000

Data Index: 290090 (C4 (Web Text))

Max Activating Token Index: 546