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

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

Neuron 2961 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2116. Min Act: -0.0002

Data Index: 288451 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2044. Min Act: -0.0002

Data Index: 641638 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2016. Min Act: -0.0002

Data Index: 1196852 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2200. Min Act: -0.0002

Data Index: 890196 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2122. Min Act: -0.0002

Data Index: 204392 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1961. Min Act: -0.0002

Data Index: 569512 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1918. Min Act: -0.0002

Data Index: 1186356 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1922. Min Act: -0.0002

Data Index: 709024 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1976. Min Act: -0.0002

Data Index: 259676 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1815. Min Act: -0.0002

Data Index: 1188382 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1805. Min Act: -0.0002

Data Index: 227960 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1552. Min Act: -0.0002

Data Index: 863082 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1776. Min Act: -0.0002

Data Index: 1288855 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1842. Min Act: -0.0002

Data Index: 58628 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2054. Min Act: -0.0002

Data Index: 450092 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1721. Min Act: -0.0002

Data Index: 817321 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1745. Min Act: -0.0002

Data Index: 667489 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1917. Min Act: -0.0002

Data Index: 738213 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1717. Min Act: -0.0002

Data Index: 1268634 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1647. Min Act: -0.0002

Data Index: 1176028 (C4 (Web Text))

Max Activating Token Index: 164