Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4586 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.2174. Min Act: -0.0000

Data Index: 462269 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1792. Min Act: -0.0000

Data Index: 224384 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1771. Min Act: -0.0000

Data Index: 359195 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1880. Min Act: -0.0000

Data Index: 460544 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1238461 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1330367 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1026030 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1876. Min Act: -0.0000

Data Index: 574777 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1774. Min Act: -0.0000

Data Index: 612540 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1610. Min Act: -0.0000

Data Index: 377840 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1647. Min Act: -0.0000

Data Index: 868557 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1644410 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1341337 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1564. Min Act: -0.0000

Data Index: 708041 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1304881 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1492. Min Act: 0.0001

Data Index: 636569 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1536. Min Act: -0.0000

Data Index: 154537 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1507. Min Act: -0.0000

Data Index: 838699 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1393. Min Act: -0.0000

Data Index: 987843 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.2174. Min Range: -0.2174

Max Act: 0.1446. Min Act: -0.0000

Data Index: 792216 (C4 (Web Text))

Max Activating Token Index: 422