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

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

Neuron 384 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: 0.5092. Min Range: -0.5092

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1019987 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1210263 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4902. Min Act: -0.0000

Data Index: 759311 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4863. Min Act: -0.0000

Data Index: 543224 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4797. Min Act: -0.0000

Data Index: 632468 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.5073. Min Act: -0.0000

Data Index: 912921 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1051888 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4654. Min Act: -0.0000

Data Index: 799805 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4811. Min Act: -0.0000

Data Index: 367169 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4757. Min Act: -0.0000

Data Index: 193665 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4482. Min Act: -0.0000

Data Index: 873141 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1317114 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4424. Min Act: -0.0000

Data Index: 23041 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4273. Min Act: -0.0000

Data Index: 655233 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4200. Min Act: -0.0000

Data Index: 256773 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4217. Min Act: -0.0000

Data Index: 367542 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4308. Min Act: -0.0000

Data Index: 177466 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1022391 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4318. Min Act: -0.0000

Data Index: 91512 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4493. Min Act: -0.0000

Data Index: 885379 (C4 (Web Text))

Max Activating Token Index: 744