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

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

Neuron 1587 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1100361 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1040418 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2149. Min Act: -0.0000

Data Index: 895382 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2112. Min Act: 0.0001

Data Index: 799564 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0558. Min Act: -0.0000

Data Index: 39659 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0659. Min Act: 0.0000

Data Index: 1207182 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0540. Min Act: -0.0000

Data Index: 153771 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1178487 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0169. Min Act: -0.0000

Data Index: 108458 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0066. Min Act: 0.0001

Data Index: 896236 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0732. Min Act: 0.0000

Data Index: 1024953 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0097. Min Act: -0.0000

Data Index: 169105 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9859. Min Act: -0.0000

Data Index: 269781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9754. Min Act: -0.0000

Data Index: 821651 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1221962 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9407. Min Act: -0.0000

Data Index: 440565 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0036. Min Act: -0.0000

Data Index: 592356 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9370. Min Act: -0.0000

Data Index: 592241 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9170. Min Act: -0.0000

Data Index: 101363 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1337278 (C4 (Web Text))

Max Activating Token Index: 898