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

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

Neuron 3 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.8844. Min Act: -0.0000

Data Index: 28403 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1265611 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.5629. Min Act: -0.0000

Data Index: 779045 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.5715. Min Act: -0.0000

Data Index: 424100 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.5580. Min Act: -0.0000

Data Index: 284263 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.5437. Min Act: -0.0000

Data Index: 828331 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4946. Min Act: -0.0000

Data Index: 213422 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4868. Min Act: -0.0000

Data Index: 61808 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.5126. Min Act: -0.0000

Data Index: 361089 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4700. Min Act: -0.0000

Data Index: 629605 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4812. Min Act: -0.0000

Data Index: 903336 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4635. Min Act: -0.0000

Data Index: 212968 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4732. Min Act: -0.0000

Data Index: 860996 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1114002 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4604. Min Act: -0.0000

Data Index: 550249 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1033721 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4119. Min Act: -0.0000

Data Index: 516131 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4156. Min Act: -0.0000

Data Index: 540100 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1047838 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1100815 (C4 (Web Text))

Max Activating Token Index: 535