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

Dataset: The Pile

Neuron 732 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: 5.0853. Min Range: -5.0853

Max Act: 5.0853. Min Act: -0.0000

Data Index: 1838021 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 5.0853. Min Range: -5.0853

Max Act: 4.4943. Min Act: -0.0000

Data Index: 1977912 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.8325. Min Act: -0.0000

Data Index: 712400 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.8448. Min Act: -0.0000

Data Index: 218927 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.7102. Min Act: -0.0000

Data Index: 346783 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.5080. Min Act: -0.0000

Data Index: 273255 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.4470. Min Act: -0.0000

Data Index: 1152559 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.0363. Min Act: -0.0000

Data Index: 345962 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.3423. Min Act: -0.0000

Data Index: 582779 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.2428. Min Act: -0.0000

Data Index: 1504911 (The Pile)

Max Activating Token Index: 432

Text #10

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.1515. Min Act: -0.0000

Data Index: 3878 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 5.0853. Min Range: -5.0853

Max Act: 2.8707. Min Act: -0.0000

Data Index: 1651098 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.2047. Min Act: -0.0000

Data Index: 1679668 (The Pile)

Max Activating Token Index: 627

Text #13

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.1788. Min Act: -0.0000

Data Index: 677310 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.1357. Min Act: -0.0000

Data Index: 1794810 (The Pile)

Max Activating Token Index: 11

Text #15

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.0990. Min Act: -0.0000

Data Index: 153082 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.1140. Min Act: -0.0000

Data Index: 396947 (The Pile)

Max Activating Token Index: 237

Text #17

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.1112. Min Act: -0.0000

Data Index: 421170 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 5.0853. Min Range: -5.0853

Max Act: 3.1002. Min Act: -0.0000

Data Index: 753741 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 5.0853. Min Range: -5.0853

Max Act: 2.9313. Min Act: -0.0000

Data Index: 610386 (The Pile)

Max Activating Token Index: 95