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

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

Neuron 1729 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2619. Min Act: -0.0001

Data Index: 200850 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2458. Min Act: -0.0001

Data Index: 766030 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2449. Min Act: -0.0000

Data Index: 760637 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2215. Min Act: -0.0001

Data Index: 1226795 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2206. Min Act: -0.0001

Data Index: 412085 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2080. Min Act: -0.0001

Data Index: 1332614 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1870. Min Act: -0.0000

Data Index: 935840 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1811. Min Act: -0.0000

Data Index: 909193 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1074100 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1777. Min Act: -0.0001

Data Index: 307942 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1792. Min Act: -0.0001

Data Index: 1074057 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1565. Min Act: -0.0001

Data Index: 862736 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1683. Min Act: -0.0001

Data Index: 959314 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1090352 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1405. Min Act: -0.0001

Data Index: 909687 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1132794 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1383. Min Act: -0.0001

Data Index: 899727 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1065625 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1488. Min Act: -0.0000

Data Index: 431174 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1350. Min Act: -0.0001

Data Index: 545562 (C4 (Web Text))

Max Activating Token Index: 182