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

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

Neuron 2706 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1825. Min Act: -0.0001

Data Index: 816900 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1067438 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1741. Min Act: -0.0001

Data Index: 798054 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1801. Min Act: -0.0001

Data Index: 370040 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1766. Min Act: -0.0001

Data Index: 445679 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1640. Min Act: -0.0001

Data Index: 550487 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1658. Min Act: -0.0001

Data Index: 656999 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1808. Min Act: -0.0001

Data Index: 692688 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1722. Min Act: -0.0001

Data Index: 882284 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1695. Min Act: -0.0001

Data Index: 15695 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1683. Min Act: -0.0001

Data Index: 542358 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1735. Min Act: -0.0001

Data Index: 983604 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1677. Min Act: -0.0001

Data Index: 1124117 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1183850 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1523. Min Act: -0.0001

Data Index: 59952 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1642. Min Act: -0.0001

Data Index: 139989 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1577. Min Act: -0.0001

Data Index: 939922 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1562. Min Act: -0.0001

Data Index: 209070 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1554. Min Act: -0.0001

Data Index: 217070 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1223039 (C4 (Web Text))

Max Activating Token Index: 956