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

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

Neuron 1515 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1358758 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.7545. Min Act: -0.0001

Data Index: 345957 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.7071. Min Act: -0.0000

Data Index: 936935 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.7060. Min Act: -0.0001

Data Index: 9310 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6981. Min Act: -0.0001

Data Index: 1175830 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6907. Min Act: -0.0001

Data Index: 148963 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6647. Min Act: -0.0000

Data Index: 139297 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.7236. Min Act: -0.0000

Data Index: 110515 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6746. Min Act: -0.0001

Data Index: 477299 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6731. Min Act: -0.0001

Data Index: 351885 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6372. Min Act: -0.0001

Data Index: 35343 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6674. Min Act: -0.0001

Data Index: 911575 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6828. Min Act: -0.0001

Data Index: 632045 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6413. Min Act: -0.0001

Data Index: 67985 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6794. Min Act: -0.0001

Data Index: 212573 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6367. Min Act: -0.0001

Data Index: 977482 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6712. Min Act: -0.0000

Data Index: 735219 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6338. Min Act: -0.0001

Data Index: 1220193 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6500. Min Act: -0.0001

Data Index: 26796 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6533. Min Act: -0.0001

Data Index: 1205011 (C4 (Web Text))

Max Activating Token Index: 177