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

Dataset: The Pile

Neuron 4808 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.0728. Min Act: 0.0000

Data Index: 1811693 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1863040 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1572492 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9983. Min Act: -0.0000

Data Index: 714172 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9430. Min Act: -0.0000

Data Index: 878561 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9031. Min Act: 0.0000

Data Index: 1229983 (The Pile)

Max Activating Token Index: 167

Text #6

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8693. Min Act: -0.0000

Data Index: 330608 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9575. Min Act: -0.0000

Data Index: 917930 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8954. Min Act: -0.0000

Data Index: 355265 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1080645 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1012541 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8763. Min Act: -0.0000

Data Index: 408326 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1256802 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9082. Min Act: -0.0000

Data Index: 501224 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8201. Min Act: -0.0000

Data Index: 1125069 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8930. Min Act: -0.0000

Data Index: 598479 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8582. Min Act: -0.0000

Data Index: 227970 (The Pile)

Max Activating Token Index: 237

Text #17

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1314181 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1652450 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8666. Min Act: 0.0000

Data Index: 602121 (The Pile)

Max Activating Token Index: 935