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

Dataset: The Pile

Neuron 2561 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.5381. Min Act: -0.0000

Data Index: 1454292 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.4920. Min Act: -0.0000

Data Index: 304824 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.3927. Min Act: -0.0000

Data Index: 1938634 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.2503. Min Act: -0.0000

Data Index: 710534 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.2463. Min Act: -0.0000

Data Index: 867005 (The Pile)

Max Activating Token Index: 155

Text #5

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.2358. Min Act: -0.0000

Data Index: 338652 (The Pile)

Max Activating Token Index: 936

Text #6

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.2408. Min Act: -0.0000

Data Index: 821587 (The Pile)

Max Activating Token Index: 501

Text #7

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.2194. Min Act: -0.0000

Data Index: 1157014 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1167460 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1644. Min Act: -0.0000

Data Index: 489413 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1704. Min Act: -0.0000

Data Index: 1565048 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0914. Min Act: -0.0000

Data Index: 281738 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1699063 (The Pile)

Max Activating Token Index: 168

Text #13

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1492047 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1970872 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.2074. Min Act: -0.0000

Data Index: 1642445 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 1.5381. Min Range: -1.5381

Max Act: 0.9937. Min Act: -0.0000

Data Index: 942704 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1307. Min Act: -0.0000

Data Index: 65340 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1044778 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 1.5381. Min Range: -1.5381

Max Act: 0.9743. Min Act: -0.0000

Data Index: 50480 (The Pile)

Max Activating Token Index: 986