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

Dataset: The Pile

Neuron 382 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: 1.5218. Min Range: -1.5218

Max Act: 1.4224. Min Act: -0.0000

Data Index: 1899304 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.5218. Min Act: -0.0000

Data Index: 1387144 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.4433. Min Act: -0.0000

Data Index: 1212884 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1685187 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1778824 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1955595 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.2926. Min Act: -0.0000

Data Index: 1548439 (The Pile)

Max Activating Token Index: 717

Text #7

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1440673 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1369954 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1068501 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.3051. Min Act: -0.0000

Data Index: 346667 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1925545 (The Pile)

Max Activating Token Index: 850

Text #12

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.3812. Min Act: -0.0000

Data Index: 1617282 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.1925. Min Act: -0.0000

Data Index: 377102 (The Pile)

Max Activating Token Index: 671

Text #14

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.2659. Min Act: -0.0000

Data Index: 984075 (The Pile)

Max Activating Token Index: 300

Text #15

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1695366 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.1828. Min Act: -0.0000

Data Index: 1373371 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.1452. Min Act: -0.0000

Data Index: 882662 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.2569. Min Act: -0.0000

Data Index: 37726 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.1766. Min Act: -0.0000

Data Index: 864972 (The Pile)

Max Activating Token Index: 813