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

Dataset: The Pile

Neuron 4278 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: 0.9482. Min Range: -0.9482

Max Act: 0.8711. Min Act: -0.0000

Data Index: 168505 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1408587 (The Pile)

Max Activating Token Index: 624

Text #2

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8455. Min Act: -0.0000

Data Index: 176740 (The Pile)

Max Activating Token Index: 657

Text #3

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7452. Min Act: -0.0000

Data Index: 320982 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7209. Min Act: -0.0000

Data Index: 147872 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7849. Min Act: -0.0000

Data Index: 401920 (The Pile)

Max Activating Token Index: 515

Text #6

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7958. Min Act: -0.0000

Data Index: 891598 (The Pile)

Max Activating Token Index: 542

Text #7

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7114. Min Act: -0.0000

Data Index: 221037 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.6817. Min Act: -0.0000

Data Index: 789370 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1800671 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1613072 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1280630 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7222. Min Act: -0.0000

Data Index: 210536 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1469991 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7029. Min Act: -0.0000

Data Index: 776346 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1765662 (The Pile)

Max Activating Token Index: 29

Text #16

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.6936. Min Act: -0.0000

Data Index: 86126 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1628860 (The Pile)

Max Activating Token Index: 445

Text #18

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1022991 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.6797. Min Act: -0.0000

Data Index: 334227 (The Pile)

Max Activating Token Index: 167