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

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

Neuron 4144 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8074. Min Act: -0.0000

Data Index: 32668 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 1.0087. Min Range: -1.0087

Max Act: 1.0087. Min Act: -0.0000

Data Index: 81897 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1320195 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8535. Min Act: -0.0000

Data Index: 573843 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1240405 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7855. Min Act: -0.0000

Data Index: 375848 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7798. Min Act: -0.0000

Data Index: 2327 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1164301 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8298. Min Act: -0.0001

Data Index: 616470 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8180. Min Act: -0.0000

Data Index: 470772 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7944. Min Act: -0.0000

Data Index: 603019 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1025919 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7220. Min Act: -0.0000

Data Index: 992649 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8085. Min Act: -0.0000

Data Index: 5767 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.8094. Min Act: -0.0000

Data Index: 415878 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1263144 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7533. Min Act: -0.0000

Data Index: 218300 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7654. Min Act: -0.0000

Data Index: 429081 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1355561 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.0087. Min Range: -1.0087

Max Act: 0.7173. Min Act: -0.0000

Data Index: 234393 (C4 (Web Text))

Max Activating Token Index: 268