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

Dataset: The Pile

Neuron 1327 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: 1.5022. Min Range: -1.5022

Max Act: 1.5022. Min Act: -0.0000

Data Index: 346520 (The Pile)

Max Activating Token Index: 240

Text #1

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1232789 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1344931 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1915243 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.2456. Min Act: -0.0000

Data Index: 1892529 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1412992 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.1085. Min Act: -0.0000

Data Index: 1683479 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1250947 (The Pile)

Max Activating Token Index: 936

Text #8

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1440067 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1888842 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0886. Min Act: -0.0000

Data Index: 412491 (The Pile)

Max Activating Token Index: 226

Text #11

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.1123. Min Act: -0.0000

Data Index: 1340602 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.1185. Min Act: -0.0000

Data Index: 228104 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0431. Min Act: -0.0000

Data Index: 26011 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 1.5022. Min Range: -1.5022

Max Act: 0.9744. Min Act: -0.0000

Data Index: 799100 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1110747 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1942443 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0353. Min Act: -0.0000

Data Index: 576342 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0234. Min Act: -0.0000

Data Index: 854483 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 1.5022. Min Range: -1.5022

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1763930 (The Pile)

Max Activating Token Index: 689