Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 462 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1001183 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2512. Min Act: -0.0000

Data Index: 914027 (The Pile)

Max Activating Token Index: 850

Text #2

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2037. Min Act: -0.0000

Data Index: 32259 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2010. Min Act: -0.0000

Data Index: 192351 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1136215 (The Pile)

Max Activating Token Index: 770

Text #5

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1713257 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2206. Min Act: -0.0000

Data Index: 126053 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1629059 (The Pile)

Max Activating Token Index: 100

Text #8

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1769. Min Act: -0.0000

Data Index: 312017 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1821. Min Act: -0.0000

Data Index: 735406 (The Pile)

Max Activating Token Index: 694

Text #10

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1300348 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1001000 (The Pile)

Max Activating Token Index: 899

Text #12

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1537423 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1870860 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1819. Min Act: -0.0000

Data Index: 602350 (The Pile)

Max Activating Token Index: 277

Text #15

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1517523 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1742. Min Act: -0.0000

Data Index: 969312 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1787. Min Act: -0.0000

Data Index: 296787 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1360430 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1729. Min Act: -0.0000

Data Index: 969021 (The Pile)

Max Activating Token Index: 405