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

Dataset: The Pile

Neuron 4803 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.5456. Min Act: -0.0000

Data Index: 1538131 (The Pile)

Max Activating Token Index: 347

Text #1

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.3641. Min Act: -0.0000

Data Index: 1035668 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.0957. Min Act: -0.0000

Data Index: 1433581 (The Pile)

Max Activating Token Index: 767

Text #3

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.3043. Min Act: -0.0000

Data Index: 1724354 (The Pile)

Max Activating Token Index: 250

Text #4

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1008752 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1595299 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1072204 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 1.5456. Min Range: -1.5456

Max Act: 1.0687. Min Act: -0.0000

Data Index: 140231 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.8912. Min Act: -0.0000

Data Index: 819652 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.8796. Min Act: -0.0000

Data Index: 21677 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1576878 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1361404 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1030499 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.8373. Min Act: -0.0000

Data Index: 526579 (The Pile)

Max Activating Token Index: 381

Text #14

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1626554 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1775043 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.7758. Min Act: -0.0000

Data Index: 187865 (The Pile)

Max Activating Token Index: 706

Text #17

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1603900 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.8311. Min Act: -0.0000

Data Index: 707627 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 1.5456. Min Range: -1.5456

Max Act: 0.7899. Min Act: -0.0000

Data Index: 186430 (The Pile)

Max Activating Token Index: 35