Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5326 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1263145 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6994. Min Act: -0.0001

Data Index: 769215 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.7102. Min Act: -0.0001

Data Index: 203231 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6399. Min Act: -0.0001

Data Index: 1009643 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5501. Min Act: -0.0001

Data Index: 75172 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4795. Min Act: -0.0001

Data Index: 811394 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5609. Min Act: -0.0001

Data Index: 178676 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5349. Min Act: -0.0001

Data Index: 318824 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4814. Min Act: -0.0001

Data Index: 476857 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4370. Min Act: -0.0001

Data Index: 766620 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4224. Min Act: -0.0001

Data Index: 48407 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4061. Min Act: -0.0001

Data Index: 883292 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4249. Min Act: -0.0001

Data Index: 113119 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4225. Min Act: -0.0001

Data Index: 766488 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.3500. Min Act: -0.0001

Data Index: 543327 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4486. Min Act: -0.0001

Data Index: 55273 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1213957 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.3875. Min Act: -0.0001

Data Index: 684447 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4105. Min Act: -0.0001

Data Index: 1114693 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.3770. Min Act: -0.0001

Data Index: 944130 (C4 (Web Text))

Max Activating Token Index: 817