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

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

Neuron 516 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.3726. Min Act: -0.0000

Data Index: 922185 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.4213. Min Act: -0.0000

Data Index: 396400 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.2082. Min Act: -0.0000

Data Index: 55305 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.3332. Min Act: -0.0000

Data Index: 602348 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.0705. Min Act: -0.0000

Data Index: 10235 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1315317 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1153. Min Act: -0.0000

Data Index: 230155 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1102. Min Act: -0.0000

Data Index: 31513 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.0200. Min Act: -0.0000

Data Index: 927304 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1139. Min Act: -0.0000

Data Index: 159347 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1013518 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.0285. Min Act: -0.0000

Data Index: 403702 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9576. Min Act: -0.0000

Data Index: 90018 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.0468. Min Act: -0.0000

Data Index: 394230 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.0052. Min Act: -0.0000

Data Index: 2160 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.0037. Min Act: -0.0000

Data Index: 454752 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9118. Min Act: -0.0000

Data Index: 432168 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9896. Min Act: -0.0000

Data Index: 539130 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9804. Min Act: -0.0000

Data Index: 224062 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1276837 (C4 (Web Text))

Max Activating Token Index: 232