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

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

Neuron 1354 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1617. Min Act: -0.0002

Data Index: 695909 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1599. Min Act: -0.0002

Data Index: 1130503 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1524. Min Act: -0.0002

Data Index: 175503 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1653. Min Act: -0.0002

Data Index: 1356765 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1649. Min Act: -0.0002

Data Index: 870580 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1581. Min Act: -0.0002

Data Index: 260128 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1690. Min Act: -0.0002

Data Index: 838867 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1610. Min Act: -0.0002

Data Index: 849901 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1654. Min Act: -0.0002

Data Index: 104734 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1710. Min Act: -0.0002

Data Index: 835565 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1546. Min Act: -0.0002

Data Index: 2143 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1573. Min Act: -0.0002

Data Index: 646561 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1558. Min Act: -0.0002

Data Index: 921195 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1615. Min Act: -0.0002

Data Index: 1357632 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1559. Min Act: -0.0002

Data Index: 1249748 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1471. Min Act: -0.0002

Data Index: 38890 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1472. Min Act: -0.0002

Data Index: 1336691 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1590. Min Act: -0.0002

Data Index: 1183084 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1511. Min Act: -0.0002

Data Index: 820211 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1559. Min Act: -0.0002

Data Index: 502995 (C4 (Web Text))

Max Activating Token Index: 413