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

Dataset: The Pile

Neuron 3441 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: 5.7179. Min Range: -5.7179

Max Act: 5.2017. Min Act: -0.0000

Data Index: 1018308 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.7179. Min Act: -0.0000

Data Index: 838210 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 5.7179. Min Range: -5.7179

Max Act: 4.2806. Min Act: -0.0000

Data Index: 782491 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.2995. Min Act: -0.0000

Data Index: 1032593 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 5.7179. Min Range: -5.7179

Max Act: 3.9467. Min Act: -0.0000

Data Index: 87298 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 5.7179. Min Range: -5.7179

Max Act: 4.1158. Min Act: -0.0000

Data Index: 548553 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 5.7179. Min Range: -5.7179

Max Act: 4.5959. Min Act: -0.0000

Data Index: 22934 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 5.7179. Min Range: -5.7179

Max Act: 4.0815. Min Act: -0.0000

Data Index: 1627156 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 5.7179. Min Range: -5.7179

Max Act: 4.3919. Min Act: -0.0000

Data Index: 1838051 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 5.7179. Min Range: -5.7179

Max Act: 3.7679. Min Act: -0.0000

Data Index: 286077 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 5.7179. Min Range: -5.7179

Max Act: 4.3176. Min Act: -0.0000

Data Index: 134665 (The Pile)

Max Activating Token Index: 598

Text #11

Max Range: 5.7179. Min Range: -5.7179

Max Act: 3.8109. Min Act: -0.0000

Data Index: 1594195 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 5.7179. Min Range: -5.7179

Max Act: 3.5999. Min Act: -0.0000

Data Index: 646734 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 5.7179. Min Range: -5.7179

Max Act: 3.7054. Min Act: -0.0000

Data Index: 791794 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 5.7179. Min Range: -5.7179

Max Act: 3.5561. Min Act: -0.0000

Data Index: 462223 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 5.7179. Min Range: -5.7179

Max Act: 3.8581. Min Act: -0.0000

Data Index: 1540402 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 5.7179. Min Range: -5.7179

Max Act: 4.1576. Min Act: -0.0000

Data Index: 1862670 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 5.7179. Min Range: -5.7179

Max Act: 3.8309. Min Act: -0.0000

Data Index: 1701694 (The Pile)

Max Activating Token Index: 1021

Text #18

Max Range: 5.7179. Min Range: -5.7179

Max Act: 3.3316. Min Act: -0.0000

Data Index: 1685274 (The Pile)

Max Activating Token Index: 972

Text #19

Max Range: 5.7179. Min Range: -5.7179

Max Act: 3.6989. Min Act: -0.0000

Data Index: 847961 (The Pile)

Max Activating Token Index: 237