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

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

Neuron 4904 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: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0002

Data Index: 776429 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0689. Min Act: -0.0002

Data Index: 73821 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0635. Min Act: -0.0002

Data Index: 133815 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0631. Min Act: -0.0002

Data Index: 97107 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0640. Min Act: -0.0002

Data Index: 436517 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0559. Min Act: -0.0002

Data Index: 622078 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1266289 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0562. Min Act: -0.0002

Data Index: 840217 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1359457 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0584. Min Act: -0.0002

Data Index: 782273 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0571. Min Act: -0.0002

Data Index: 773680 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1230000 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0552. Min Act: -0.0002

Data Index: 771979 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1306781 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0507. Min Act: -0.0002

Data Index: 993426 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0535. Min Act: -0.0002

Data Index: 800565 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1036637 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0531. Min Act: -0.0002

Data Index: 221650 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0514. Min Act: -0.0002

Data Index: 464180 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0530. Min Act: -0.0002

Data Index: 598680 (C4 (Web Text))

Max Activating Token Index: 150