Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3625 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.8698. Min Act: -0.0001

Data Index: 802496 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7872. Min Act: -0.0002

Data Index: 966179 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6933. Min Act: -0.0001

Data Index: 1110976 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7014. Min Act: -0.0001

Data Index: 10936 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7220. Min Act: -0.0002

Data Index: 164222 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7874. Min Act: -0.0002

Data Index: 896900 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7524. Min Act: -0.0002

Data Index: 667717 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6985. Min Act: -0.0002

Data Index: 121376 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7104. Min Act: -0.0002

Data Index: 847598 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6124. Min Act: -0.0002

Data Index: 1081408 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6914. Min Act: -0.0002

Data Index: 809079 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6699. Min Act: -0.0001

Data Index: 1230972 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6770. Min Act: -0.0002

Data Index: 368250 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6307. Min Act: -0.0002

Data Index: 639890 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6674. Min Act: -0.0002

Data Index: 1334315 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6744. Min Act: -0.0002

Data Index: 635658 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.5750. Min Act: -0.0001

Data Index: 1048916 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6265. Min Act: -0.0002

Data Index: 1117287 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6407. Min Act: -0.0001

Data Index: 38517 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6341. Min Act: -0.0001

Data Index: 980024 (C4 (Web Text))

Max Activating Token Index: 175