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

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

Neuron 1888 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1573. Min Act: -0.0001

Data Index: 664523 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1402. Min Act: -0.0001

Data Index: 266772 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1307443 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1377. Min Act: -0.0001

Data Index: 779814 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1347. Min Act: -0.0001

Data Index: 967342 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1309. Min Act: -0.0001

Data Index: 762132 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1292. Min Act: -0.0001

Data Index: 1150149 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1174. Min Act: -0.0001

Data Index: 588730 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1193. Min Act: -0.0000

Data Index: 180662 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1282164 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1113. Min Act: -0.0001

Data Index: 903354 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1176. Min Act: -0.0001

Data Index: 937085 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1044087 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1057109 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1162. Min Act: -0.0001

Data Index: 730593 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1207. Min Act: -0.0001

Data Index: 243535 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1127. Min Act: -0.0001

Data Index: 432099 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1112. Min Act: -0.0000

Data Index: 388286 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1096200 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1087. Min Act: -0.0000

Data Index: 794458 (C4 (Web Text))

Max Activating Token Index: 184