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

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

Neuron 4057 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1010011 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5954. Min Act: -0.0000

Data Index: 342977 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5881. Min Act: -0.0000

Data Index: 341383 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5108. Min Act: -0.0000

Data Index: 926881 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1246708 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5308. Min Act: -0.0000

Data Index: 133024 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5152. Min Act: -0.0000

Data Index: 551385 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4945. Min Act: -0.0000

Data Index: 624829 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5285. Min Act: -0.0000

Data Index: 28978 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5102. Min Act: -0.0000

Data Index: 202187 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5174. Min Act: -0.0000

Data Index: 708989 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5008. Min Act: -0.0000

Data Index: 478902 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4843. Min Act: -0.0000

Data Index: 955162 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5027. Min Act: -0.0000

Data Index: 490073 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5013. Min Act: -0.0000

Data Index: 600379 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1107900 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4873. Min Act: -0.0000

Data Index: 88329 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1077509 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1063014 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1232950 (C4 (Web Text))

Max Activating Token Index: 524