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

Dataset: The Pile

Neuron 1841 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: 1.0759. Min Range: -1.0759

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1538689 (The Pile)

Max Activating Token Index: 707

Text #1

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1865659 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1465601 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1632921 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1395078 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1080469 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9585. Min Act: -0.0000

Data Index: 1239371 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1164281 (The Pile)

Max Activating Token Index: 239

Text #8

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1055524 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9784. Min Act: -0.0000

Data Index: 959891 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8421. Min Act: -0.0000

Data Index: 287986 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8963. Min Act: -0.0000

Data Index: 416998 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1974854 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8855. Min Act: -0.0000

Data Index: 563270 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1022991 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1433263 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8608. Min Act: -0.0000

Data Index: 370206 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8617. Min Act: -0.0000

Data Index: 147872 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8366. Min Act: -0.0000

Data Index: 818669 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7386. Min Act: -0.0000

Data Index: 361864 (The Pile)

Max Activating Token Index: 659