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

Dataset: The Pile

Neuron 2083 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: 1.5042. Min Range: -1.5042

Max Act: 1.4557. Min Act: -0.0000

Data Index: 531919 (The Pile)

Max Activating Token Index: 835

Text #1

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.4266. Min Act: -0.0000

Data Index: 306539 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.5042. Min Act: -0.0000

Data Index: 330450 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.4078. Min Act: -0.0000

Data Index: 1633954 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.4106. Min Act: -0.0000

Data Index: 739696 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.3714. Min Act: -0.0000

Data Index: 800790 (The Pile)

Max Activating Token Index: 788

Text #6

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2297. Min Act: -0.0000

Data Index: 163863 (The Pile)

Max Activating Token Index: 783

Text #7

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.3801. Min Act: -0.0000

Data Index: 1297841 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.3321. Min Act: -0.0000

Data Index: 942985 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2888. Min Act: -0.0000

Data Index: 1044053 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2727. Min Act: -0.0000

Data Index: 826233 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2520. Min Act: -0.0000

Data Index: 1047571 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2551. Min Act: -0.0000

Data Index: 115748 (The Pile)

Max Activating Token Index: 749

Text #13

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2543. Min Act: -0.0000

Data Index: 1904523 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2558. Min Act: -0.0000

Data Index: 50646 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1109517 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2733. Min Act: -0.0000

Data Index: 1559408 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2561. Min Act: -0.0000

Data Index: 1581103 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2209. Min Act: -0.0000

Data Index: 1283959 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 1.5042. Min Range: -1.5042

Max Act: 1.2177. Min Act: -0.0000

Data Index: 1846262 (The Pile)

Max Activating Token Index: 1022