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

Dataset: The Pile

Neuron 2519 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.7612. Min Act: -0.0000

Data Index: 1726589 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.7155. Min Act: -0.0000

Data Index: 1550264 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.5589. Min Act: -0.0000

Data Index: 626868 (The Pile)

Max Activating Token Index: 541

Text #3

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.5851. Min Act: -0.0000

Data Index: 1173607 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.5815. Min Act: -0.0000

Data Index: 420316 (The Pile)

Max Activating Token Index: 610

Text #5

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.6031. Min Act: -0.0000

Data Index: 645135 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.4830. Min Act: -0.0000

Data Index: 1158057 (The Pile)

Max Activating Token Index: 705

Text #7

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1818265 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1297156 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.4484. Min Act: -0.0000

Data Index: 511177 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.2641. Min Act: -0.0000

Data Index: 1171658 (The Pile)

Max Activating Token Index: 530

Text #11

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.1225. Min Act: -0.0000

Data Index: 624602 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.2000. Min Act: -0.0000

Data Index: 599982 (The Pile)

Max Activating Token Index: 94

Text #13

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.2860. Min Act: -0.0000

Data Index: 1253412 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.0772. Min Act: -0.0000

Data Index: 528262 (The Pile)

Max Activating Token Index: 547

Text #15

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1965323 (The Pile)

Max Activating Token Index: 216

Text #16

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1346374 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.2662. Min Act: -0.0000

Data Index: 850603 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1989960 (The Pile)

Max Activating Token Index: 498

Text #19

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.4328. Min Act: -0.0000

Data Index: 1265314 (The Pile)

Max Activating Token Index: 1015