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

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

Neuron 3706 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.5521. Min Act: -0.0000

Data Index: 950360 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.5652. Min Act: -0.0000

Data Index: 946647 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.5564. Min Act: -0.0000

Data Index: 259906 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.5145. Min Act: -0.0000

Data Index: 56649 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.5058. Min Act: -0.0000

Data Index: 649674 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4658. Min Act: -0.0000

Data Index: 902036 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1040891 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4840. Min Act: -0.0000

Data Index: 672942 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4677. Min Act: -0.0000

Data Index: 998468 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4768. Min Act: -0.0000

Data Index: 190255 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1044718 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4482. Min Act: -0.0000

Data Index: 280663 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1243124 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4296. Min Act: -0.0000

Data Index: 800501 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1234091 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4369. Min Act: -0.0000

Data Index: 172665 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1096488 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4640. Min Act: -0.0000

Data Index: 48124 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4419. Min Act: -0.0000

Data Index: 75562 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1155294 (C4 (Web Text))

Max Activating Token Index: 892