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

Dataset: The Pile

Neuron 2681 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1414161 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1254095 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6132. Min Act: -0.0000

Data Index: 281723 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1603926 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6296. Min Act: -0.0000

Data Index: 301836 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1355484 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5810. Min Act: 0.0000

Data Index: 790035 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1205503 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1941677 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1111933 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1267425 (The Pile)

Max Activating Token Index: 913

Text #11

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1678923 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1841685 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5547. Min Act: -0.0000

Data Index: 754021 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4933. Min Act: -0.0000

Data Index: 653349 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1113045 (The Pile)

Max Activating Token Index: 946

Text #16

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5333. Min Act: -0.0001

Data Index: 1767153 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1639153 (The Pile)

Max Activating Token Index: 848

Text #18

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5080. Min Act: -0.0000

Data Index: 979127 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1328092 (The Pile)

Max Activating Token Index: 844