Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5701 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2945. Min Range: -4.2945

Max Act: 4.2945. Min Act: -0.0000

Data Index: 1230877 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 4.2945. Min Range: -4.2945

Max Act: 3.5441. Min Act: -0.0000

Data Index: 825326 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 4.2945. Min Range: -4.2945

Max Act: 3.2125. Min Act: -0.0000

Data Index: 442307 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 4.2945. Min Range: -4.2945

Max Act: 3.1744. Min Act: -0.0000

Data Index: 1330008 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.9615. Min Act: -0.0000

Data Index: 350482 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 4.2945. Min Range: -4.2945

Max Act: 3.0814. Min Act: -0.0000

Data Index: 324381 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.9354. Min Act: -0.0000

Data Index: 713411 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.9395. Min Act: -0.0000

Data Index: 488677 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 4.2945. Min Range: -4.2945

Max Act: 3.0352. Min Act: -0.0000

Data Index: 508504 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.9913. Min Act: -0.0000

Data Index: 1267355 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 4.2945. Min Range: -4.2945

Max Act: 3.1574. Min Act: -0.0000

Data Index: 943206 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.6610. Min Act: -0.0000

Data Index: 614476 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 4.2945. Min Range: -4.2945

Max Act: 3.0997. Min Act: -0.0000

Data Index: 411254 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.8976. Min Act: -0.0000

Data Index: 768 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.8769. Min Act: -0.0000

Data Index: 952106 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.5018. Min Act: -0.0000

Data Index: 1312353 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 4.2945. Min Range: -4.2945

Max Act: 3.0368. Min Act: -0.0000

Data Index: 1343558 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.7013. Min Act: -0.0000

Data Index: 645990 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.6457. Min Act: -0.0000

Data Index: 1090938 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 4.2945. Min Range: -4.2945

Max Act: 2.5812. Min Act: -0.0000

Data Index: 200835 (C4 (Web Text))

Max Activating Token Index: 194