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

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

Neuron 805 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.6766. Min Act: -0.0001

Data Index: 840962 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.6450. Min Act: -0.0001

Data Index: 1165334 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.5968. Min Act: -0.0001

Data Index: 975462 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.5836. Min Act: -0.0001

Data Index: 420976 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.6173. Min Act: -0.0001

Data Index: 233770 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4959. Min Act: -0.0001

Data Index: 1252713 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.5858. Min Act: -0.0001

Data Index: 18888 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.5349. Min Act: -0.0001

Data Index: 299529 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4898. Min Act: -0.0001

Data Index: 241270 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.5159. Min Act: -0.0001

Data Index: 606365 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4855. Min Act: -0.0001

Data Index: 569472 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4581. Min Act: -0.0001

Data Index: 838025 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4845. Min Act: -0.0001

Data Index: 1016817 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4566. Min Act: -0.0001

Data Index: 846956 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4254. Min Act: -0.0001

Data Index: 1209386 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4565. Min Act: -0.0001

Data Index: 329625 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4142. Min Act: -0.0001

Data Index: 828485 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4322. Min Act: -0.0001

Data Index: 177974 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4789. Min Act: -0.0001

Data Index: 950152 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.6766. Min Range: -0.6766

Max Act: 0.4032. Min Act: -0.0001

Data Index: 866411 (C4 (Web Text))

Max Activating Token Index: 254