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

Dataset: The Pile

Neuron 847 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: 1.0468. Min Range: -1.0468

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1159692 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1011422 (The Pile)

Max Activating Token Index: 903

Text #2

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1698809 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1966790 (The Pile)

Max Activating Token Index: 942

Text #4

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.9301. Min Act: -0.0000

Data Index: 581602 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1393152 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1526950 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1201994 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7940. Min Act: -0.0000

Data Index: 142312 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7811. Min Act: -0.0000

Data Index: 776683 (The Pile)

Max Activating Token Index: 38

Text #10

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1220281 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1544496 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1908350 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7864. Min Act: -0.0000

Data Index: 912158 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1280905 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1450044 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7528. Min Act: -0.0000

Data Index: 987596 (The Pile)

Max Activating Token Index: 384

Text #17

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7275. Min Act: -0.0000

Data Index: 91530 (The Pile)

Max Activating Token Index: 515

Text #18

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7230. Min Act: -0.0000

Data Index: 116804 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1366723 (The Pile)

Max Activating Token Index: 816