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

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

Neuron 1751 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: 0.0389. Min Range: -0.0389

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1055888 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0366. Min Act: -0.0002

Data Index: 892575 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0362. Min Act: -0.0002

Data Index: 86278 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0378. Min Act: -0.0002

Data Index: 162877 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0381. Min Act: -0.0002

Data Index: 838190 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1035853 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0372. Min Act: -0.0002

Data Index: 725453 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0365. Min Act: -0.0002

Data Index: 661693 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0360. Min Act: -0.0002

Data Index: 425237 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0366. Min Act: -0.0002

Data Index: 81449 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1316356 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0332. Min Act: -0.0002

Data Index: 434826 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1207215 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0366. Min Act: -0.0002

Data Index: 749436 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0349. Min Act: -0.0002

Data Index: 418420 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0343. Min Act: -0.0002

Data Index: 854785 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1038326 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0353. Min Act: -0.0002

Data Index: 375973 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1096964 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0351. Min Act: -0.0002

Data Index: 607368 (C4 (Web Text))

Max Activating Token Index: 63