Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3797 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0840. Min Act: -0.0001

Data Index: 731307 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0854. Min Act: -0.0001

Data Index: 684686 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0755. Min Act: -0.0002

Data Index: 275371 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1213159 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1133300 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0649. Min Act: -0.0002

Data Index: 184390 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0627. Min Act: -0.0001

Data Index: 436338 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0657. Min Act: -0.0001

Data Index: 680354 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0679. Min Act: -0.0002

Data Index: 193661 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1426338 (Python Code)

Max Activating Token Index: 928

Text #10

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0649. Min Act: -0.0001

Data Index: 416035 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0629. Min Act: -0.0001

Data Index: 294526 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1606651 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0604. Min Act: -0.0001

Data Index: 414399 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0627. Min Act: -0.0001

Data Index: 201354 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1539124 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1439195 (Python Code)

Max Activating Token Index: 62

Text #17

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1615515 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0590. Min Act: -0.0001

Data Index: 779343 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1055690 (C4 (Web Text))

Max Activating Token Index: 658