Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1673 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1260321 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1634. Min Act: -0.0001

Data Index: 826343 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1473. Min Act: -0.0001

Data Index: 250392 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1441. Min Act: -0.0001

Data Index: 725238 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1401. Min Act: -0.0001

Data Index: 695558 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1264. Min Act: -0.0001

Data Index: 79915 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1356. Min Act: -0.0001

Data Index: 181407 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1289. Min Act: -0.0001

Data Index: 758147 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1222. Min Act: -0.0001

Data Index: 737145 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1299759 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1172. Min Act: -0.0001

Data Index: 866289 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1163136 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1116666 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1099. Min Act: -0.0000

Data Index: 851646 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1143. Min Act: -0.0001

Data Index: 929377 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1021615 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1175940 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1246629 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1094093 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1135. Min Act: -0.0001

Data Index: 315567 (C4 (Web Text))

Max Activating Token Index: 383