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

Dataset: The Pile

Neuron 3053 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1121930 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1342928 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1306705 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1691221 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4864. Min Act: -0.0000

Data Index: 101308 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4848. Min Act: -0.0000

Data Index: 650248 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1728701 (The Pile)

Max Activating Token Index: 580

Text #7

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4618. Min Act: -0.0000

Data Index: 678138 (The Pile)

Max Activating Token Index: 625

Text #8

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1738130 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1560625 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4366. Min Act: -0.0000

Data Index: 180296 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1095483 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1301444 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1745385 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4109. Min Act: -0.0000

Data Index: 598190 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4210. Min Act: -0.0000

Data Index: 248086 (The Pile)

Max Activating Token Index: 454

Text #16

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1839906 (The Pile)

Max Activating Token Index: 477

Text #17

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1018107 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3989. Min Act: -0.0000

Data Index: 186122 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4074. Min Act: -0.0000

Data Index: 124249 (The Pile)

Max Activating Token Index: 686