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

Dataset: The Pile

Neuron 487 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1943. Min Range: -1.1943

Max Act: 1.1943. Min Act: 0.0000

Data Index: 128657 (The Pile)

Max Activating Token Index: 194

Text #1

Max Range: 1.1943. Min Range: -1.1943

Max Act: 1.0820. Min Act: 0.0000

Data Index: 966395 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 1.1943. Min Range: -1.1943

Max Act: 1.1377. Min Act: -0.0000

Data Index: 958599 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 1.1943. Min Range: -1.1943

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1718269 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 1.1943. Min Range: -1.1943

Max Act: 1.0542. Min Act: -0.0000

Data Index: 340918 (The Pile)

Max Activating Token Index: 641

Text #5

Max Range: 1.1943. Min Range: -1.1943

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1666240 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.9153. Min Act: 0.0000

Data Index: 1471905 (The Pile)

Max Activating Token Index: 779

Text #7

Max Range: 1.1943. Min Range: -1.1943

Max Act: 1.0649. Min Act: -0.0000

Data Index: 1859614 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 1.1943. Min Range: -1.1943

Max Act: 1.0011. Min Act: -0.0000

Data Index: 15416 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.9991. Min Act: 0.0000

Data Index: 1532412 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.9787. Min Act: 0.0000

Data Index: 1622536 (The Pile)

Max Activating Token Index: 722

Text #11

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1024556 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8913. Min Act: -0.0000

Data Index: 964375 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1724794 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1461738 (The Pile)

Max Activating Token Index: 925

Text #15

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8826. Min Act: -0.0000

Data Index: 97983 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8698. Min Act: 0.0000

Data Index: 944547 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1660361 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1626923 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8495. Min Act: -0.0000

Data Index: 458652 (The Pile)

Max Activating Token Index: 613