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

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

Neuron 2200 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1685. Min Act: -0.0001

Data Index: 781431 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1597. Min Act: -0.0001

Data Index: 4645 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1086441 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1596. Min Act: -0.0001

Data Index: 394372 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1191639 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1310448 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1446. Min Act: -0.0001

Data Index: 190801 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1219626 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1305252 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1230. Min Act: -0.0001

Data Index: 966921 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1196034 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1305. Min Act: -0.0001

Data Index: 236894 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1216. Min Act: -0.0001

Data Index: 719695 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1323439 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1351772 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1208. Min Act: -0.0001

Data Index: 523872 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1113. Min Act: -0.0001

Data Index: 449678 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1276390 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1058. Min Act: -0.0001

Data Index: 386597 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1139. Min Act: -0.0001

Data Index: 900693 (C4 (Web Text))

Max Activating Token Index: 120