Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1435 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0872. Min Act: -0.0003

Data Index: 469603 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0732. Min Act: -0.0002

Data Index: 250328 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1031472 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0703. Min Act: -0.0002

Data Index: 388075 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0683. Min Act: -0.0002

Data Index: 786060 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0675. Min Act: -0.0002

Data Index: 330543 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0659. Min Act: -0.0003

Data Index: 279521 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0650. Min Act: -0.0003

Data Index: 777599 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0634. Min Act: -0.0003

Data Index: 853864 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1009450 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0641. Min Act: -0.0003

Data Index: 608772 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1087828 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1153931 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0609. Min Act: -0.0003

Data Index: 224917 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0626. Min Act: -0.0003

Data Index: 189807 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1251582 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0608. Min Act: -0.0003

Data Index: 651430 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1038585 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0603. Min Act: -0.0003

Data Index: 693845 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0592. Min Act: 0.0000

Data Index: 745537 (C4 (Web Text))

Max Activating Token Index: 638