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

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

Neuron 3024 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1176964 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1898. Min Act: -0.0000

Data Index: 576765 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1779. Min Act: -0.0000

Data Index: 153639 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1680. Min Act: -0.0000

Data Index: 552925 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1353291 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1646. Min Act: -0.0000

Data Index: 598595 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1565. Min Act: -0.0000

Data Index: 301827 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1660. Min Act: -0.0000

Data Index: 71658 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1590. Min Act: -0.0000

Data Index: 266637 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1269461 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1542. Min Act: -0.0000

Data Index: 711416 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1691. Min Act: -0.0000

Data Index: 172046 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1652. Min Act: -0.0000

Data Index: 1223716 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1575. Min Act: -0.0000

Data Index: 240439 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1546. Min Act: -0.0000

Data Index: 883528 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1533. Min Act: -0.0000

Data Index: 875696 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1256215 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1538. Min Act: -0.0000

Data Index: 961501 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1422. Min Act: -0.0000

Data Index: 948299 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1504. Min Act: -0.0001

Data Index: 1168713 (C4 (Web Text))

Max Activating Token Index: 812