Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 325 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1313348 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1208. Min Act: -0.0000

Data Index: 183651 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0940. Min Act: -0.0000

Data Index: 658616 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0978. Min Act: -0.0000

Data Index: 762791 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1107025 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1934529 (The Pile)

Max Activating Token Index: 285

Text #6

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0811. Min Act: -0.0000

Data Index: 230165 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0844. Min Act: -0.0000

Data Index: 898857 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1084573 (The Pile)

Max Activating Token Index: 467

Text #9

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0747. Min Act: -0.0000

Data Index: 869821 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0722. Min Act: -0.0000

Data Index: 812392 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1161432 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1888368 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1393712 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0748. Min Act: -0.0000

Data Index: 1875997 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1132220 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1461856 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1095723 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0706. Min Act: -0.0000

Data Index: 244548 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1223521 (The Pile)

Max Activating Token Index: 191