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

Dataset: The Pile

Neuron 1993 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: 0.8873. Min Range: -0.8873

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1531655 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.8069. Min Act: -0.0000

Data Index: 972992 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7857. Min Act: 0.0000

Data Index: 590160 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7300. Min Act: -0.0000

Data Index: 508303 (The Pile)

Max Activating Token Index: 616

Text #4

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7184. Min Act: -0.0000

Data Index: 467036 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1571768 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7153. Min Act: -0.0000

Data Index: 627906 (The Pile)

Max Activating Token Index: 572

Text #7

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1124469 (The Pile)

Max Activating Token Index: 909

Text #8

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1985864 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7542. Min Act: -0.0000

Data Index: 804423 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7179. Min Act: -0.0000

Data Index: 711093 (The Pile)

Max Activating Token Index: 376

Text #11

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6588. Min Act: -0.0000

Data Index: 222804 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1208365 (The Pile)

Max Activating Token Index: 839

Text #13

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1727752 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6591. Min Act: -0.0000

Data Index: 986341 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1534869 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1250780 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1994923 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6467. Min Act: -0.0000

Data Index: 362852 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1279684 (The Pile)

Max Activating Token Index: 81