Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1386 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.2189. Min Act: -0.0002

Data Index: 91469 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.2139. Min Act: -0.0002

Data Index: 776599 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.2033. Min Act: -0.0002

Data Index: 740239 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1991. Min Act: -0.0002

Data Index: 714179 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1853. Min Act: -0.0002

Data Index: 577895 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1932. Min Act: -0.0002

Data Index: 1058178 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1886. Min Act: -0.0002

Data Index: 224211 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1808. Min Act: -0.0002

Data Index: 84867 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1817. Min Act: -0.0002

Data Index: 923689 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1735. Min Act: -0.0002

Data Index: 404761 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1682. Min Act: -0.0002

Data Index: 378497 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1751. Min Act: -0.0002

Data Index: 448800 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1683. Min Act: -0.0002

Data Index: 1150285 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1692. Min Act: -0.0001

Data Index: 696967 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1644. Min Act: -0.0002

Data Index: 450197 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1696. Min Act: -0.0002

Data Index: 371067 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1620. Min Act: -0.0002

Data Index: 112325 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1628. Min Act: -0.0002

Data Index: 918543 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1620. Min Act: -0.0002

Data Index: 1264331 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1607. Min Act: -0.0002

Data Index: 1288067 (C4 (Web Text))

Max Activating Token Index: 971