Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2614 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1787. Min Act: -0.0001

Data Index: 508184 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1809. Min Act: -0.0001

Data Index: 288648 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1727. Min Act: -0.0001

Data Index: 872911 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1670. Min Act: -0.0001

Data Index: 732551 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1669. Min Act: -0.0001

Data Index: 360744 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1691. Min Act: -0.0001

Data Index: 362022 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1666. Min Act: -0.0001

Data Index: 418929 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1591. Min Act: -0.0001

Data Index: 342974 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1257488 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1609. Min Act: -0.0001

Data Index: 534819 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1583. Min Act: -0.0001

Data Index: 826706 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1565. Min Act: -0.0001

Data Index: 775188 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1562. Min Act: -0.0001

Data Index: 941405 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1572. Min Act: -0.0001

Data Index: 64652 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1178393 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1564. Min Act: -0.0001

Data Index: 259115 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1546. Min Act: -0.0001

Data Index: 846088 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1519. Min Act: -0.0001

Data Index: 537175 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1565. Min Act: -0.0001

Data Index: 788368 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1547. Min Act: -0.0001

Data Index: 1651615 (Python Code)

Max Activating Token Index: 547