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

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

Neuron 1750 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3248. Min Range: -2.3248

Max Act: 2.3248. Min Act: -0.0000

Data Index: 805376 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 2.3248. Min Range: -2.3248

Max Act: 2.2021. Min Act: -0.0000

Data Index: 893345 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 2.3248. Min Range: -2.3248

Max Act: 2.2010. Min Act: -0.0000

Data Index: 1184286 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 2.3248. Min Range: -2.3248

Max Act: 2.1180. Min Act: -0.0000

Data Index: 782775 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 2.3248. Min Range: -2.3248

Max Act: 2.0999. Min Act: -0.0000

Data Index: 257475 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 2.3248. Min Range: -2.3248

Max Act: 2.0083. Min Act: -0.0000

Data Index: 212067 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 2.3248. Min Range: -2.3248

Max Act: 2.1159. Min Act: -0.0000

Data Index: 179349 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.9077. Min Act: -0.0000

Data Index: 239558 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.7758. Min Act: -0.0000

Data Index: 1241505 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.7661. Min Act: -0.0000

Data Index: 812412 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.8297. Min Act: -0.0000

Data Index: 505405 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.7607. Min Act: -0.0000

Data Index: 1101640 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.7459. Min Act: -0.0000

Data Index: 1318278 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.8219. Min Act: -0.0000

Data Index: 57621 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.7253. Min Act: -0.0000

Data Index: 482980 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.7045. Min Act: -0.0000

Data Index: 1021315 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.7019. Min Act: -0.0000

Data Index: 45053 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.7917. Min Act: -0.0000

Data Index: 189476 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.6409. Min Act: -0.0000

Data Index: 559098 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 2.3248. Min Range: -2.3248

Max Act: 1.6167. Min Act: -0.0000

Data Index: 1228405 (C4 (Web Text))

Max Activating Token Index: 410