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

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

Neuron 1835 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.5701. Min Act: -0.0000

Data Index: 731001 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.5196. Min Act: -0.0000

Data Index: 860136 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4891. Min Act: -0.0000

Data Index: 62750 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1161331 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4606. Min Act: -0.0000

Data Index: 155868 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4557. Min Act: -0.0000

Data Index: 204731 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1351797 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1140314 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1183482 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1028288 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4243. Min Act: -0.0000

Data Index: 348474 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4093. Min Act: -0.0000

Data Index: 545552 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4343. Min Act: -0.0000

Data Index: 373816 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1521406 (Python Code)

Max Activating Token Index: 758

Text #14

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1249058 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3714. Min Act: -0.0000

Data Index: 403548 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3804. Min Act: -0.0000

Data Index: 904127 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3795. Min Act: -0.0000

Data Index: 154977 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1244530 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1284763 (C4 (Web Text))

Max Activating Token Index: 720