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

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

Neuron 3647 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: 2.1165. Min Range: -2.1165

Max Act: 2.1159. Min Act: -0.0000

Data Index: 844573 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 2.1165. Min Range: -2.1165

Max Act: 2.1165. Min Act: -0.0000

Data Index: 1116953 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.9294. Min Act: -0.0000

Data Index: 414771 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.9170. Min Act: -0.0000

Data Index: 662606 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.7878. Min Act: -0.0000

Data Index: 1185651 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.7884. Min Act: -0.0000

Data Index: 470181 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.9381. Min Act: -0.0000

Data Index: 1208632 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.5809. Min Act: -0.0000

Data Index: 1510200 (Python Code)

Max Activating Token Index: 929

Text #8

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.5648. Min Act: -0.0000

Data Index: 744970 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.6066. Min Act: -0.0000

Data Index: 832891 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.5149. Min Act: -0.0000

Data Index: 1452577 (Python Code)

Max Activating Token Index: 607

Text #11

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.5267. Min Act: -0.0000

Data Index: 604419 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.4280. Min Act: -0.0000

Data Index: 979311 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.5602. Min Act: -0.0000

Data Index: 792616 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1138793 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.4145. Min Act: -0.0000

Data Index: 1086705 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.3979. Min Act: -0.0000

Data Index: 775070 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1150558 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.3838. Min Act: -0.0000

Data Index: 716174 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 2.1165. Min Range: -2.1165

Max Act: 1.3796. Min Act: -0.0000

Data Index: 433936 (C4 (Web Text))

Max Activating Token Index: 62