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

Dataset: The Pile

Neuron 4207 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1708802 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1041032 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.9312. Min Act: -0.0000

Data Index: 967291 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1528241 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1950765 (The Pile)

Max Activating Token Index: 620

Text #5

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1283208 (The Pile)

Max Activating Token Index: 878

Text #6

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1826242 (The Pile)

Max Activating Token Index: 685

Text #7

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.9018. Min Act: -0.0000

Data Index: 215476 (The Pile)

Max Activating Token Index: 839

Text #8

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8171. Min Act: -0.0000

Data Index: 469041 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1897860 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7998. Min Act: -0.0000

Data Index: 621813 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1401288 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8969. Min Act: -0.0000

Data Index: 668217 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1800464 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1794639 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1945690 (The Pile)

Max Activating Token Index: 117

Text #16

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8008. Min Act: -0.0000

Data Index: 864168 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1702765 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7448. Min Act: -0.0000

Data Index: 1835411 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7338. Min Act: -0.0000

Data Index: 526118 (The Pile)

Max Activating Token Index: 831