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

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

Neuron 1522 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: 0.6709. Min Range: -0.6709

Max Act: 0.6709. Min Act: -0.0000

Data Index: 287825 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1220756 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4029. Min Act: -0.0000

Data Index: 70957 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4125. Min Act: -0.0000

Data Index: 466844 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4002. Min Act: -0.0000

Data Index: 543532 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1577769 (Python Code)

Max Activating Token Index: 183

Text #6

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1110137 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1254608 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3830. Min Act: -0.0000

Data Index: 177596 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1241593 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3648. Min Act: -0.0000

Data Index: 636016 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3447. Min Act: -0.0000

Data Index: 849907 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3567. Min Act: -0.0000

Data Index: 649394 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3353. Min Act: -0.0000

Data Index: 797798 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3035. Min Act: -0.0000

Data Index: 70651 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3303. Min Act: -0.0000

Data Index: 630801 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3147. Min Act: -0.0000

Data Index: 859251 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1285561 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3161. Min Act: -0.0000

Data Index: 687121 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.3122. Min Act: -0.0000

Data Index: 1037942 (C4 (Web Text))

Max Activating Token Index: 166