Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5577 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1492. Min Act: -0.0001

Data Index: 1158677 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1334. Min Act: -0.0001

Data Index: 1152405 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1349. Min Act: -0.0000

Data Index: 538431 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1391. Min Act: -0.0000

Data Index: 692870 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1036206 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1238. Min Act: -0.0000

Data Index: 949275 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1355. Min Act: -0.0000

Data Index: 666692 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1254. Min Act: -0.0000

Data Index: 767391 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1217. Min Act: -0.0000

Data Index: 989710 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1298. Min Act: -0.0001

Data Index: 797792 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1212. Min Act: -0.0001

Data Index: 738107 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1164. Min Act: -0.0000

Data Index: 221221 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1166. Min Act: -0.0000

Data Index: 11713 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1115. Min Act: -0.0001

Data Index: 1285970 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1102. Min Act: -0.0001

Data Index: 942590 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1224458 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1079. Min Act: -0.0001

Data Index: 867929 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1076. Min Act: -0.0000

Data Index: 311586 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1132. Min Act: -0.0001

Data Index: 161414 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1066. Min Act: -0.0000

Data Index: 739936 (C4 (Web Text))

Max Activating Token Index: 399