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

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

Neuron 3141 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.7747. Min Act: -0.0000

Data Index: 550691 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1327841 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.7365. Min Act: -0.0000

Data Index: 658370 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6687. Min Act: -0.0000

Data Index: 252051 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1169411 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6931. Min Act: -0.0000

Data Index: 376726 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6471. Min Act: -0.0000

Data Index: 970716 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1206189 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6171. Min Act: -0.0000

Data Index: 256384 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1284222 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6068. Min Act: -0.0000

Data Index: 581504 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1198689 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6109. Min Act: -0.0000

Data Index: 624476 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5720. Min Act: -0.0000

Data Index: 353245 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6040. Min Act: -0.0000

Data Index: 331880 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5856. Min Act: -0.0000

Data Index: 668426 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5972. Min Act: -0.0000

Data Index: 31122 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6400. Min Act: -0.0000

Data Index: 662523 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5911. Min Act: -0.0000

Data Index: 46995 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5707. Min Act: -0.0000

Data Index: 231655 (C4 (Web Text))

Max Activating Token Index: 151