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

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

Neuron 3674 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1501089 (Python Code)

Max Activating Token Index: 626

Text #1

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1544186 (Python Code)

Max Activating Token Index: 969

Text #2

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1454765 (Python Code)

Max Activating Token Index: 883

Text #3

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4677. Min Act: -0.0000

Data Index: 236963 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3750. Min Act: -0.0000

Data Index: 121792 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4055. Min Act: -0.0000

Data Index: 990424 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4213. Min Act: -0.0000

Data Index: 123137 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1438399 (Python Code)

Max Activating Token Index: 981

Text #8

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1001325 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.4023. Min Act: -0.0000

Data Index: 80791 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3815. Min Act: -0.0000

Data Index: 976541 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3761. Min Act: -0.0000

Data Index: 626895 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3571. Min Act: -0.0000

Data Index: 105671 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1432788 (Python Code)

Max Activating Token Index: 673

Text #14

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3653. Min Act: -0.0000

Data Index: 158977 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3425. Min Act: -0.0000

Data Index: 472764 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1390452 (Python Code)

Max Activating Token Index: 431

Text #17

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1510176 (Python Code)

Max Activating Token Index: 777

Text #18

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3214. Min Act: -0.0000

Data Index: 855701 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1654977 (Python Code)

Max Activating Token Index: 620