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

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

Neuron 3843 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: 1.3627. Min Range: -1.3627

Max Act: 1.3627. Min Act: -0.0000

Data Index: 862631 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.3001. Min Act: -0.0000

Data Index: 70455 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1256545 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.2735. Min Act: -0.0000

Data Index: 357555 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.2575. Min Act: -0.0000

Data Index: 808502 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.1908. Min Act: -0.0000

Data Index: 711017 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.1047. Min Act: -0.0000

Data Index: 638877 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.1186. Min Act: -0.0000

Data Index: 399306 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.0601. Min Act: -0.0000

Data Index: 237572 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1011868 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.0544. Min Act: -0.0000

Data Index: 1303280 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.0393. Min Act: -0.0000

Data Index: 309431 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.0673. Min Act: -0.0000

Data Index: 794440 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.0277. Min Act: -0.0000

Data Index: 240332 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.0517. Min Act: -0.0000

Data Index: 1238574 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1321198 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.0113. Min Act: -0.0000

Data Index: 105003 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 1.3627. Min Range: -1.3627

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1195886 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1329232 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 1.3627. Min Range: -1.3627

Max Act: 0.9920. Min Act: -0.0000

Data Index: 986774 (C4 (Web Text))

Max Activating Token Index: 559