Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1458. Min Act: -0.0005

Data Index: 548044 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1327. Min Act: -0.0005

Data Index: 429406 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1287. Min Act: -0.0005

Data Index: 427567 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1314. Min Act: -0.0005

Data Index: 583137 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1210. Min Act: -0.0005

Data Index: 305219 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1248. Min Act: -0.0005

Data Index: 635488 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1186. Min Act: -0.0005

Data Index: 504231 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1243. Min Act: -0.0005

Data Index: 795253 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1201. Min Act: -0.0005

Data Index: 445924 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1179. Min Act: -0.0005

Data Index: 608763 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1201. Min Act: -0.0005

Data Index: 388140 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1198. Min Act: -0.0005

Data Index: 1144136 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1180. Min Act: -0.0005

Data Index: 277875 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1140. Min Act: -0.0005

Data Index: 602817 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1189. Min Act: -0.0005

Data Index: 350403 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1175. Min Act: -0.0005

Data Index: 1162468 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1134. Min Act: -0.0005

Data Index: 852617 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1120. Min Act: -0.0005

Data Index: 172806 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1204. Min Act: -0.0005

Data Index: 800596 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1186. Min Act: -0.0005

Data Index: 44961 (C4 (Web Text))

Max Activating Token Index: 984