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

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

Neuron 4574 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: 0.1618. Min Range: -0.1618

Max Act: 0.1618. Min Act: -0.0000

Data Index: 846159 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1297. Min Act: -0.0000

Data Index: 656301 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1274. Min Act: -0.0000

Data Index: 705639 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1167336 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1211. Min Act: -0.0000

Data Index: 616509 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1053317 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1221735 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1060585 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1171. Min Act: -0.0000

Data Index: 184884 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1141. Min Act: -0.0000

Data Index: 223425 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1122617 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1056. Min Act: -0.0000

Data Index: 395766 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1112. Min Act: -0.0000

Data Index: 594399 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1105. Min Act: -0.0000

Data Index: 562438 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1294976 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1312653 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1039. Min Act: -0.0000

Data Index: 906976 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1100. Min Act: -0.0000

Data Index: 411487 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1259886 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1084. Min Act: -0.0000

Data Index: 305534 (C4 (Web Text))

Max Activating Token Index: 721