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

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

Neuron 228 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: 0.1773. Min Range: -0.1773

Max Act: 0.1773. Min Act: -0.0000

Data Index: 259232 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1074350 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1524. Min Act: -0.0000

Data Index: 540579 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1601. Min Act: -0.0000

Data Index: 867272 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1518. Min Act: -0.0000

Data Index: 159811 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1482. Min Act: -0.0000

Data Index: 102294 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1062544 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1376. Min Act: -0.0000

Data Index: 958695 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1103189 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1015335 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1375. Min Act: -0.0000

Data Index: 94994 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1205. Min Act: -0.0000

Data Index: 781342 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1225363 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1254. Min Act: -0.0000

Data Index: 518868 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1283. Min Act: -0.0000

Data Index: 644237 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1019128 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1190. Min Act: -0.0000

Data Index: 179335 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1285. Min Act: -0.0000

Data Index: 420188 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1212779 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1172779 (C4 (Web Text))

Max Activating Token Index: 507