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

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

Neuron 2155 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1811. Min Act: -0.0002

Data Index: 604072 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1458. Min Act: -0.0002

Data Index: 100796 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1435. Min Act: -0.0002

Data Index: 199872 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1066716 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1417. Min Act: -0.0002

Data Index: 640427 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1406. Min Act: -0.0002

Data Index: 1085769 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1454. Min Act: -0.0002

Data Index: 43158 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1273. Min Act: -0.0002

Data Index: 300852 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1268. Min Act: -0.0002

Data Index: 732042 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1260. Min Act: -0.0002

Data Index: 924033 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1220. Min Act: -0.0002

Data Index: 1321864 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1219. Min Act: -0.0002

Data Index: 317975 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1136. Min Act: -0.0002

Data Index: 990979 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1055. Min Act: -0.0002

Data Index: 861867 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1137576 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1173. Min Act: -0.0002

Data Index: 158597 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1351156 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1192. Min Act: -0.0002

Data Index: 1187295 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1159. Min Act: -0.0002

Data Index: 955771 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1293. Min Act: -0.0002

Data Index: 1002122 (C4 (Web Text))

Max Activating Token Index: 966