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

Dataset: The Pile

Neuron 4754 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: 1.8962. Min Range: -1.8962

Max Act: 1.8962. Min Act: -0.0000

Data Index: 742117 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.6789. Min Act: -0.0000

Data Index: 895525 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.5770. Min Act: -0.0000

Data Index: 1807542 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.5200. Min Act: -0.0000

Data Index: 1456226 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.6132. Min Act: -0.0000

Data Index: 1960267 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.4847. Min Act: -0.0000

Data Index: 287247 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.4501. Min Act: -0.0000

Data Index: 1494673 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.4088. Min Act: -0.0000

Data Index: 1965268 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.4814. Min Act: -0.0000

Data Index: 256400 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.3366. Min Act: -0.0000

Data Index: 30873 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.3924. Min Act: -0.0000

Data Index: 159037 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.2510. Min Act: -0.0000

Data Index: 1740192 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.2132. Min Act: -0.0000

Data Index: 373251 (The Pile)

Max Activating Token Index: 883

Text #13

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.1887. Min Act: -0.0000

Data Index: 6375 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.2181. Min Act: -0.0000

Data Index: 1281704 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1597227 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1649057 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1547024 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.0628. Min Act: -0.0000

Data Index: 229923 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 1.8962. Min Range: -1.8962

Max Act: 1.1476. Min Act: -0.0000

Data Index: 1594165 (The Pile)

Max Activating Token Index: 260