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

Dataset: The Pile

Neuron 567 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: 1.0028. Min Range: -1.0028

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1654591 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.9464. Min Act: -0.0000

Data Index: 621253 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.9979. Min Act: -0.0000

Data Index: 162427 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.9503. Min Act: -0.0000

Data Index: 793003 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8402. Min Act: -0.0000

Data Index: 15840 (The Pile)

Max Activating Token Index: 961

Text #5

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1655464 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8583. Min Act: -0.0000

Data Index: 27213 (The Pile)

Max Activating Token Index: 954

Text #7

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8580. Min Act: -0.0000

Data Index: 462176 (The Pile)

Max Activating Token Index: 529

Text #8

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7984. Min Act: -0.0000

Data Index: 413908 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8207. Min Act: -0.0000

Data Index: 299850 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8373. Min Act: -0.0000

Data Index: 276405 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1409813 (The Pile)

Max Activating Token Index: 950

Text #12

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1917795 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1643653 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7924. Min Act: -0.0000

Data Index: 99955 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1609568 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1684917 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7647. Min Act: -0.0000

Data Index: 53667 (The Pile)

Max Activating Token Index: 685

Text #18

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8232. Min Act: -0.0000

Data Index: 219295 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7566. Min Act: -0.0000

Data Index: 520867 (The Pile)

Max Activating Token Index: 550