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

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

Neuron 894 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0912. Min Act: -0.0002

Data Index: 147920 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0861. Min Act: -0.0002

Data Index: 362676 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1333547 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1234715 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0766. Min Act: -0.0002

Data Index: 415824 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0640. Min Act: -0.0002

Data Index: 435831 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1071218 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1042603 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0552. Min Act: -0.0002

Data Index: 270260 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1177084 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1100790 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0551. Min Act: -0.0002

Data Index: 263817 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0550. Min Act: -0.0002

Data Index: 321992 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0525. Min Act: -0.0002

Data Index: 766839 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1210445 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0535. Min Act: -0.0002

Data Index: 855276 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1093673 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0515. Min Act: -0.0002

Data Index: 234303 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1232299 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0513. Min Act: -0.0002

Data Index: 694928 (C4 (Web Text))

Max Activating Token Index: 860