Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 255 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1981. Min Act: -0.0001

Data Index: 521510 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1126793 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1670. Min Act: -0.0001

Data Index: 103810 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1191802 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1784. Min Act: -0.0001

Data Index: 773643 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1724. Min Act: -0.0001

Data Index: 949479 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1641. Min Act: -0.0001

Data Index: 931940 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1715. Min Act: -0.0001

Data Index: 664227 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1695. Min Act: -0.0001

Data Index: 585934 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1147957 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1691. Min Act: -0.0001

Data Index: 925976 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1629. Min Act: -0.0001

Data Index: 584198 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1717. Min Act: -0.0001

Data Index: 540180 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1634. Min Act: -0.0001

Data Index: 334743 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1570. Min Act: -0.0001

Data Index: 91066 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1518. Min Act: -0.0001

Data Index: 343177 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1352496 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1199623 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1620. Min Act: -0.0001

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1130355 (C4 (Web Text))

Max Activating Token Index: 275