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

Dataset: The Pile

Neuron 2110 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: 0.6007. Min Range: -0.6007

Max Act: 0.6007. Min Act: -0.0000

Data Index: 57836 (The Pile)

Max Activating Token Index: 508

Text #1

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1432492 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1770834 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5858. Min Act: -0.0000

Data Index: 118558 (The Pile)

Max Activating Token Index: 813

Text #4

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4913. Min Act: -0.0000

Data Index: 211121 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5220. Min Act: -0.0000

Data Index: 833856 (The Pile)

Max Activating Token Index: 351

Text #6

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4990. Min Act: -0.0000

Data Index: 847505 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4614. Min Act: -0.0000

Data Index: 559566 (The Pile)

Max Activating Token Index: 525

Text #8

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4821. Min Act: -0.0000

Data Index: 356060 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4644. Min Act: -0.0000

Data Index: 96075 (The Pile)

Max Activating Token Index: 824

Text #10

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4354. Min Act: -0.0000

Data Index: 808039 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4659. Min Act: -0.0000

Data Index: 227687 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1814730 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1364606 (The Pile)

Max Activating Token Index: 848

Text #14

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1098826 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1636994 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1263252 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1234600 (The Pile)

Max Activating Token Index: 815

Text #18

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1633400 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1433616 (The Pile)

Max Activating Token Index: 715