Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3184 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7696. Min Act: -0.0002

Data Index: 519999 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7800. Min Act: -0.0001

Data Index: 1071237 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8604. Min Act: -0.0002

Data Index: 298993 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7920. Min Act: -0.0002

Data Index: 391564 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7690. Min Act: -0.0001

Data Index: 423327 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7647. Min Act: -0.0002

Data Index: 178478 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7155. Min Act: -0.0002

Data Index: 405636 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7053. Min Act: -0.0002

Data Index: 1280086 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7671. Min Act: -0.0002

Data Index: 565107 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7951. Min Act: -0.0002

Data Index: 440098 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8129. Min Act: -0.0002

Data Index: 1225748 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7742. Min Act: -0.0002

Data Index: 1102000 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7049. Min Act: -0.0001

Data Index: 622959 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7450. Min Act: -0.0002

Data Index: 1234979 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6941. Min Act: -0.0001

Data Index: 533130 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7049. Min Act: -0.0002

Data Index: 1293802 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7272. Min Act: -0.0002

Data Index: 843742 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7631. Min Act: -0.0002

Data Index: 401426 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6806. Min Act: -0.0002

Data Index: 776090 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7433. Min Act: -0.0001

Data Index: 743096 (C4 (Web Text))

Max Activating Token Index: 864