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

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

Neuron 4796 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: 0.1835. Min Range: -0.1835

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1003427 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1777. Min Act: -0.0001

Data Index: 1012403 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1575. Min Act: -0.0001

Data Index: 605005 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1697. Min Act: -0.0001

Data Index: 281819 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1633. Min Act: -0.0001

Data Index: 552177 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1416. Min Act: -0.0001

Data Index: 859650 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1575. Min Act: -0.0001

Data Index: 15679 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1555. Min Act: -0.0001

Data Index: 775894 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1337519 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1114504 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1390. Min Act: -0.0001

Data Index: 599366 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1400. Min Act: -0.0001

Data Index: 745773 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1505. Min Act: -0.0001

Data Index: 419797 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1424. Min Act: -0.0001

Data Index: 73890 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1392. Min Act: -0.0001

Data Index: 36239 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1058969 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1010534 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1102875 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1488. Min Act: -0.0001

Data Index: 909816 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1251729 (C4 (Web Text))

Max Activating Token Index: 19