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

Dataset: The Pile

Neuron 1539 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: 1.5526. Min Range: -1.5526

Max Act: 1.5526. Min Act: -0.0000

Data Index: 1459399 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.3016. Min Act: -0.0000

Data Index: 498483 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1681. Min Act: -0.0000

Data Index: 640674 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.0551. Min Act: -0.0000

Data Index: 1228298 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1768720 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1895238 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9622. Min Act: -0.0000

Data Index: 355381 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.0041. Min Act: 0.0000

Data Index: 1174142 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.0218. Min Act: -0.0000

Data Index: 789852 (The Pile)

Max Activating Token Index: 737

Text #9

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9359. Min Act: -0.0000

Data Index: 249971 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1907876 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9626. Min Act: -0.0000

Data Index: 481152 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8971. Min Act: -0.0000

Data Index: 757831 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1696820 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8732. Min Act: -0.0000

Data Index: 549105 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8931. Min Act: -0.0000

Data Index: 165735 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1253965 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8868. Min Act: -0.0000

Data Index: 456476 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8831. Min Act: -0.0000

Data Index: 416892 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1979413 (The Pile)

Max Activating Token Index: 79