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

Dataset: The Pile

Neuron 3750 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.5482. Min Act: -0.0000

Data Index: 521524 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.3115. Min Act: -0.0000

Data Index: 733308 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.2122. Min Act: -0.0000

Data Index: 223848 (The Pile)

Max Activating Token Index: 174

Text #3

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.1570. Min Act: -0.0000

Data Index: 465147 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.1238. Min Act: -0.0000

Data Index: 1510002 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.1519. Min Act: -0.0000

Data Index: 307859 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.1078. Min Act: -0.0000

Data Index: 387981 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1871931 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1654653 (The Pile)

Max Activating Token Index: 918

Text #9

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.0780. Min Act: -0.0000

Data Index: 895452 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.1043. Min Act: -0.0000

Data Index: 524937 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.0990. Min Act: -0.0000

Data Index: 1512166 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.0628. Min Act: -0.0000

Data Index: 631432 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1274487 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1431022 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1512990 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1943250 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 1.5482. Min Range: -1.5482

Max Act: 0.9487. Min Act: -0.0000

Data Index: 380922 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1944398 (The Pile)

Max Activating Token Index: 337

Text #19

Max Range: 1.5482. Min Range: -1.5482

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1409823 (The Pile)

Max Activating Token Index: 443