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

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

Neuron 2628 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1351. Min Act: -0.0000

Data Index: 38763 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1290. Min Act: -0.0000

Data Index: 934626 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1276. Min Act: -0.0000

Data Index: 745565 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1285297 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1143. Min Act: -0.0000

Data Index: 556626 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1268. Min Act: -0.0000

Data Index: 553258 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1209. Min Act: -0.0000

Data Index: 362128 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1290530 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1177. Min Act: -0.0000

Data Index: 923130 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1139. Min Act: -0.0000

Data Index: 264372 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1079. Min Act: -0.0000

Data Index: 159315 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1247411 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1168818 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1033. Min Act: -0.0000

Data Index: 104679 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1034. Min Act: -0.0000

Data Index: 393346 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1066. Min Act: -0.0000

Data Index: 898578 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1061. Min Act: -0.0000

Data Index: 973910 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0992. Min Act: -0.0000

Data Index: 550079 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1042. Min Act: -0.0000

Data Index: 533260 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1153023 (C4 (Web Text))

Max Activating Token Index: 791