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

Dataset: The Pile

Neuron 848 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4865. Min Act: -0.0000

Data Index: 211568 (The Pile)

Max Activating Token Index: 917

Text #1

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4060. Min Act: -0.0000

Data Index: 309632 (The Pile)

Max Activating Token Index: 628

Text #2

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3963. Min Act: -0.0000

Data Index: 294910 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1925359 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3614. Min Act: -0.0000

Data Index: 665992 (The Pile)

Max Activating Token Index: 221

Text #5

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1600403 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3336. Min Act: -0.0000

Data Index: 489672 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3496. Min Act: -0.0000

Data Index: 907374 (The Pile)

Max Activating Token Index: 119

Text #8

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3533. Min Act: -0.0000

Data Index: 212099 (The Pile)

Max Activating Token Index: 661

Text #9

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1197895 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1126061 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1471800 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1731914 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1647764 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1672724 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.2961. Min Act: -0.0000

Data Index: 30725 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1625628 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3122. Min Act: -0.0000

Data Index: 546802 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3122. Min Act: -0.0000

Data Index: 961632 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1326051 (The Pile)

Max Activating Token Index: 521