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

Dataset: The Pile

Neuron 361 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: 1.1693. Min Range: -1.1693

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1781804 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.1184. Min Act: -0.0000

Data Index: 143660 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0560. Min Act: -0.0000

Data Index: 551415 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0414. Min Act: -0.0000

Data Index: 360091 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1854155 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1200354 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0573. Min Act: -0.0000

Data Index: 768819 (The Pile)

Max Activating Token Index: 659

Text #7

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0841. Min Act: -0.0000

Data Index: 675608 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1378867 (The Pile)

Max Activating Token Index: 555

Text #9

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1562657 (The Pile)

Max Activating Token Index: 569

Text #10

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0671. Min Act: -0.0000

Data Index: 515549 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1370042 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0606. Min Act: -0.0000

Data Index: 1343978 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0255. Min Act: -0.0000

Data Index: 511814 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.1655. Min Act: -0.0000

Data Index: 927856 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1322912 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1873739 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1756266 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1886333 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9252. Min Act: -0.0000

Data Index: 1986008 (The Pile)

Max Activating Token Index: 182