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

Dataset: The Pile

Neuron 2245 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: 0.2250. Min Range: -0.2250

Max Act: 0.2044. Min Act: -0.0000

Data Index: 237777 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2213. Min Act: -0.0000

Data Index: 41847 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1146986 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2108. Min Act: -0.0000

Data Index: 653925 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2250. Min Act: -0.0000

Data Index: 784534 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1943132 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2059. Min Act: -0.0000

Data Index: 910665 (The Pile)

Max Activating Token Index: 561

Text #7

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2059. Min Act: -0.0000

Data Index: 646437 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2003. Min Act: -0.0000

Data Index: 45999 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1836. Min Act: -0.0000

Data Index: 757542 (The Pile)

Max Activating Token Index: 577

Text #10

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1201265 (The Pile)

Max Activating Token Index: 977

Text #11

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1882. Min Act: -0.0000

Data Index: 839002 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1295862 (The Pile)

Max Activating Token Index: 985

Text #13

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2043. Min Act: -0.0000

Data Index: 562728 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1701. Min Act: -0.0000

Data Index: 164366 (The Pile)

Max Activating Token Index: 448

Text #15

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1653. Min Act: -0.0000

Data Index: 209584 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1671. Min Act: -0.0000

Data Index: 859599 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1767163 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1575. Min Act: -0.0000

Data Index: 396286 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1485. Min Act: -0.0000

Data Index: 13721 (The Pile)

Max Activating Token Index: 47