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

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

Neuron 2953 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1849. Min Act: -0.0001

Data Index: 38110 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1412. Min Act: -0.0001

Data Index: 642531 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1343. Min Act: -0.0001

Data Index: 836127 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1300. Min Act: -0.0001

Data Index: 392902 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1300180 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1202658 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1266. Min Act: -0.0001

Data Index: 643092 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1188. Min Act: -0.0001

Data Index: 715595 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1114483 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1177. Min Act: -0.0001

Data Index: 94900 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1114. Min Act: -0.0001

Data Index: 1144024 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1126. Min Act: -0.0001

Data Index: 337880 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1318033 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1068. Min Act: -0.0001

Data Index: 450461 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1013. Min Act: -0.0001

Data Index: 13410 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1110. Min Act: -0.0001

Data Index: 292644 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.0994. Min Act: -0.0001

Data Index: 918593 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1077. Min Act: -0.0001

Data Index: 792762 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.0980. Min Act: -0.0001

Data Index: 355521 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1102. Min Act: -0.0001

Data Index: 28305 (C4 (Web Text))

Max Activating Token Index: 539