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

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

Neuron 1908 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: 0.2232. Min Range: -0.2232

Max Act: 0.2232. Min Act: -0.0002

Data Index: 998120 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.2164. Min Act: -0.0002

Data Index: 103458 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1922. Min Act: -0.0002

Data Index: 457165 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1905. Min Act: -0.0002

Data Index: 296512 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1820. Min Act: -0.0002

Data Index: 13927 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1751. Min Act: -0.0002

Data Index: 397121 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1750. Min Act: -0.0002

Data Index: 1094073 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1692. Min Act: -0.0002

Data Index: 244685 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1733. Min Act: -0.0002

Data Index: 1056393 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1756. Min Act: -0.0002

Data Index: 26174 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1666. Min Act: -0.0002

Data Index: 1074679 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1713. Min Act: -0.0002

Data Index: 937756 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1632. Min Act: -0.0002

Data Index: 255732 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1584. Min Act: -0.0002

Data Index: 449692 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1689. Min Act: -0.0002

Data Index: 85957 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1748. Min Act: -0.0002

Data Index: 625417 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1635. Min Act: -0.0002

Data Index: 899535 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1663. Min Act: -0.0002

Data Index: 125308 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1677. Min Act: -0.0001

Data Index: 108770 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1640. Min Act: -0.0002

Data Index: 248674 (C4 (Web Text))

Max Activating Token Index: 57