Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1633 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1913881 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6401. Min Act: -0.0000

Data Index: 293846 (The Pile)

Max Activating Token Index: 450

Text #2

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1012324 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1462201 (The Pile)

Max Activating Token Index: 948

Text #4

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1231031 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5214. Min Act: -0.0000

Data Index: 317069 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1348775 (The Pile)

Max Activating Token Index: 741

Text #7

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1440307 (The Pile)

Max Activating Token Index: 547

Text #8

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1982712 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1428697 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5716. Min Act: -0.0000

Data Index: 769122 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5694. Min Act: -0.0000

Data Index: 293310 (The Pile)

Max Activating Token Index: 987

Text #12

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5395. Min Act: -0.0000

Data Index: 916165 (The Pile)

Max Activating Token Index: 125

Text #13

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1196487 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1033283 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5648. Min Act: -0.0000

Data Index: 411925 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1728072 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.5037. Min Act: -0.0000

Data Index: 948559 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1518329 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 0.8858. Min Range: -0.8858

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1983245 (The Pile)

Max Activating Token Index: 598