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

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

Neuron 2928 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: 0.0858. Min Range: -0.0858

Max Act: 0.0858. Min Act: -0.0002

Data Index: 143372 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1023386 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1014718 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0622. Min Act: -0.0001

Data Index: 872428 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1017974 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0607. Min Act: -0.0001

Data Index: 385686 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1089465 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0563. Min Act: -0.0001

Data Index: 338377 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0555. Min Act: -0.0001

Data Index: 769510 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0563. Min Act: -0.0001

Data Index: 426763 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1286602 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0556. Min Act: -0.0002

Data Index: 23975 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0546. Min Act: -0.0001

Data Index: 322291 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1202111 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1055315 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0534. Min Act: -0.0002

Data Index: 973343 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0547. Min Act: -0.0002

Data Index: 4357 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0531. Min Act: -0.0001

Data Index: 145019 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0546. Min Act: -0.0001

Data Index: 892915 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0508. Min Act: -0.0002

Data Index: 547311 (C4 (Web Text))

Max Activating Token Index: 136