Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 241 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0002

Data Index: 120920 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1208402 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1126588 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0500. Min Act: -0.0002

Data Index: 518877 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0480. Min Act: -0.0002

Data Index: 181949 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0467. Min Act: -0.0002

Data Index: 496503 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1243337 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0428. Min Act: -0.0001

Data Index: 753232 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0447. Min Act: -0.0002

Data Index: 127823 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0455. Min Act: -0.0002

Data Index: 108213 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0457. Min Act: -0.0002

Data Index: 852831 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0423. Min Act: -0.0002

Data Index: 130787 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0441. Min Act: -0.0001

Data Index: 352963 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1129264 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1076870 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0433. Min Act: -0.0002

Data Index: 681874 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1010776 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1201737 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0401. Min Act: -0.0002

Data Index: 571196 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0395. Min Act: -0.0002

Data Index: 369797 (C4 (Web Text))

Max Activating Token Index: 537