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

Dataset: The Pile

Neuron 238 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: 0.6671. Min Range: -0.6671

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1638826 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4424. Min Act: -0.0000

Data Index: 780868 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4583. Min Act: -0.0000

Data Index: 395367 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4832. Min Act: -0.0000

Data Index: 300169 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4845. Min Act: -0.0000

Data Index: 113204 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4629. Min Act: -0.0000

Data Index: 720872 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4599. Min Act: -0.0000

Data Index: 5506 (The Pile)

Max Activating Token Index: 436

Text #7

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1287474 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4275. Min Act: -0.0000

Data Index: 662325 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1969466 (The Pile)

Max Activating Token Index: 569

Text #10

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1298653 (The Pile)

Max Activating Token Index: 425

Text #11

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1267963 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4015. Min Act: -0.0000

Data Index: 508536 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4124. Min Act: -0.0000

Data Index: 522780 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4117. Min Act: -0.0000

Data Index: 678339 (The Pile)

Max Activating Token Index: 873

Text #15

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.3968. Min Act: -0.0000

Data Index: 414077 (The Pile)

Max Activating Token Index: 662

Text #16

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.3529. Min Act: -0.0000

Data Index: 423053 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1935666 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.3691. Min Act: -0.0000

Data Index: 407364 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1344906 (The Pile)

Max Activating Token Index: 584