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

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

Neuron 1267 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1456468 (Python Code)

Max Activating Token Index: 906

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0799. Min Act: 0.0000

Data Index: 785643 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1203102 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0758. Min Act: 0.0000

Data Index: 239621 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0689. Min Act: -0.0000

Data Index: 216964 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0619. Min Act: -0.0000

Data Index: 78845 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0633. Min Act: -0.0001

Data Index: 189006 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0634. Min Act: -0.0000

Data Index: 365842 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1554973 (Python Code)

Max Activating Token Index: 844

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0633. Min Act: -0.0001

Data Index: 735122 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1533552 (Python Code)

Max Activating Token Index: 711

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1301620 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0662. Min Act: -0.0001

Data Index: 274157 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1599509 (Python Code)

Max Activating Token Index: 472

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0590. Min Act: 0.0000

Data Index: 1039380 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1392244 (Python Code)

Max Activating Token Index: 539

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0572. Min Act: 0.0000

Data Index: 1354604 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0525. Min Act: -0.0000

Data Index: 601849 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1460456 (Python Code)

Max Activating Token Index: 713

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0588. Min Act: -0.0001

Data Index: 119701 (C4 (Web Text))

Max Activating Token Index: 963