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

Dataset: The Pile

Neuron 537 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: 3.7609. Min Range: -3.7609

Max Act: 3.7609. Min Act: -0.0000

Data Index: 649709 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.5917. Min Act: -0.0000

Data Index: 1673767 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3257. Min Act: -0.0000

Data Index: 235403 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.1118. Min Act: -0.0000

Data Index: 1230161 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 3.7609. Min Range: -3.7609

Max Act: 2.9313. Min Act: -0.0000

Data Index: 1752796 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.1219. Min Act: -0.0000

Data Index: 1003522 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.0009. Min Act: -0.0000

Data Index: 551106 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 3.7609. Min Range: -3.7609

Max Act: 2.9995. Min Act: -0.0000

Data Index: 1624334 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.2903. Min Act: -0.0000

Data Index: 1305558 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.5365. Min Act: -0.0000

Data Index: 1865273 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.1873. Min Act: -0.0000

Data Index: 954075 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3267. Min Act: -0.0000

Data Index: 679505 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 3.7609. Min Range: -3.7609

Max Act: 2.9791. Min Act: -0.0000

Data Index: 244447 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 3.7609. Min Range: -3.7609

Max Act: 2.7929. Min Act: -0.0000

Data Index: 1862130 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 3.7609. Min Range: -3.7609

Max Act: 2.9395. Min Act: -0.0000

Data Index: 501532 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 3.7609. Min Range: -3.7609

Max Act: 2.9162. Min Act: -0.0000

Data Index: 73357 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.0149. Min Act: -0.0000

Data Index: 224826 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 3.7609. Min Range: -3.7609

Max Act: 2.8715. Min Act: -0.0000

Data Index: 51139 (The Pile)

Max Activating Token Index: 842

Text #18

Max Range: 3.7609. Min Range: -3.7609

Max Act: 2.8369. Min Act: -0.0000

Data Index: 1867174 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 3.7609. Min Range: -3.7609

Max Act: 2.4448. Min Act: -0.0000

Data Index: 820124 (The Pile)

Max Activating Token Index: 250