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

Dataset: The Pile

Neuron 2777 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0540. Min Act: -0.0000

Data Index: 680930 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9740. Min Act: -0.0000

Data Index: 787876 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9813. Min Act: -0.0000

Data Index: 904751 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9310. Min Act: -0.0000

Data Index: 1505358 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8899. Min Act: -0.0000

Data Index: 683133 (The Pile)

Max Activating Token Index: 625

Text #5

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9634. Min Act: -0.0000

Data Index: 290863 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8610. Min Act: -0.0000

Data Index: 656801 (The Pile)

Max Activating Token Index: 333

Text #7

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1752910 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8414. Min Act: -0.0000

Data Index: 430960 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1705917 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7699. Min Act: -0.0000

Data Index: 828139 (The Pile)

Max Activating Token Index: 582

Text #11

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1775223 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7395. Min Act: -0.0000

Data Index: 442084 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1539605 (The Pile)

Max Activating Token Index: 172

Text #14

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1943062 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8907. Min Act: -0.0000

Data Index: 248226 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8115. Min Act: -0.0000

Data Index: 568842 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1037075 (The Pile)

Max Activating Token Index: 920

Text #18

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8133. Min Act: -0.0000

Data Index: 158997 (The Pile)

Max Activating Token Index: 215

Text #19

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8083. Min Act: -0.0000

Data Index: 284236 (The Pile)

Max Activating Token Index: 6