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

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

Neuron 925 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1619. Min Act: -0.0001

Data Index: 654786 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1487. Min Act: -0.0001

Data Index: 988072 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1329. Min Act: -0.0001

Data Index: 355580 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1346. Min Act: -0.0001

Data Index: 293115 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1406. Min Act: -0.0001

Data Index: 870127 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1229059 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1310773 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1155. Min Act: -0.0001

Data Index: 953046 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1352. Min Act: -0.0001

Data Index: 2342 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1104970 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1104. Min Act: -0.0001

Data Index: 342961 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1123629 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1133. Min Act: -0.0001

Data Index: 722625 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1082. Min Act: -0.0001

Data Index: 607269 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1031365 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1046. Min Act: -0.0001

Data Index: 633398 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1054360 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1092. Min Act: -0.0001

Data Index: 397895 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1019. Min Act: -0.0001

Data Index: 275768 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1353476 (C4 (Web Text))

Max Activating Token Index: 125