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

Dataset: The Pile

Neuron 1779 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: 3.2587. Min Range: -3.2587

Max Act: 3.0480. Min Act: -0.0000

Data Index: 403425 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.8426. Min Act: -0.0000

Data Index: 1642354 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 3.2587. Min Range: -3.2587

Max Act: 3.2587. Min Act: -0.0000

Data Index: 1930261 (The Pile)

Max Activating Token Index: 1021

Text #3

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.7582. Min Act: -0.0000

Data Index: 1545883 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.7493. Min Act: -0.0000

Data Index: 464758 (The Pile)

Max Activating Token Index: 323

Text #5

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.4581. Min Act: -0.0000

Data Index: 168044 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.5678. Min Act: -0.0000

Data Index: 1884316 (The Pile)

Max Activating Token Index: 665

Text #7

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.5388. Min Act: -0.0000

Data Index: 458463 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.6821. Min Act: -0.0000

Data Index: 1232977 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.5449. Min Act: -0.0000

Data Index: 1880388 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.2970. Min Act: -0.0000

Data Index: 1449426 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.3955. Min Act: -0.0000

Data Index: 25215 (The Pile)

Max Activating Token Index: 512

Text #12

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.4868. Min Act: -0.0000

Data Index: 1914488 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.3750. Min Act: -0.0000

Data Index: 1197262 (The Pile)

Max Activating Token Index: 882

Text #14

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.6578. Min Act: -0.0000

Data Index: 267042 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.3836. Min Act: -0.0000

Data Index: 1892140 (The Pile)

Max Activating Token Index: 527

Text #16

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.5209. Min Act: -0.0000

Data Index: 10696 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.2529. Min Act: -0.0000

Data Index: 494930 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.3547. Min Act: -0.0000

Data Index: 471245 (The Pile)

Max Activating Token Index: 625

Text #19

Max Range: 3.2587. Min Range: -3.2587

Max Act: 2.3596. Min Act: -0.0000

Data Index: 1910247 (The Pile)

Max Activating Token Index: 815