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

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

Neuron 4233 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.6260. Min Act: -0.0000

Data Index: 568127 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5585. Min Act: -0.0000

Data Index: 306661 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1279717 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1208907 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5656. Min Act: -0.0000

Data Index: 606621 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5069. Min Act: -0.0000

Data Index: 155161 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4929. Min Act: -0.0000

Data Index: 343359 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4590. Min Act: -0.0000

Data Index: 380631 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4642. Min Act: -0.0000

Data Index: 809752 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4421. Min Act: -0.0000

Data Index: 47619 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4965. Min Act: -0.0000

Data Index: 687813 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4870. Min Act: -0.0000

Data Index: 32063 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4552. Min Act: -0.0000

Data Index: 662631 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1085087 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4473. Min Act: -0.0000

Data Index: 52852 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4255. Min Act: -0.0000

Data Index: 720681 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4490. Min Act: -0.0000

Data Index: 391174 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1121304 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1337429 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4471. Min Act: -0.0000

Data Index: 739302 (C4 (Web Text))

Max Activating Token Index: 835