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

Dataset: The Pile

Neuron 3651 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: 0.7536. Min Range: -0.7536

Max Act: 0.7536. Min Act: -0.0000

Data Index: 397969 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6512. Min Act: -0.0000

Data Index: 352814 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1105613 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6309. Min Act: -0.0000

Data Index: 851778 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6067. Min Act: -0.0000

Data Index: 485469 (The Pile)

Max Activating Token Index: 822

Text #5

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1583837 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1899721 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6297. Min Act: -0.0000

Data Index: 416725 (The Pile)

Max Activating Token Index: 534

Text #8

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1518878 (The Pile)

Max Activating Token Index: 403

Text #9

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6422. Min Act: -0.0000

Data Index: 255610 (The Pile)

Max Activating Token Index: 229

Text #10

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1899493 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.5789. Min Act: -0.0000

Data Index: 268040 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.5617. Min Act: -0.0000

Data Index: 236957 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1054578 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.6041. Min Act: -0.0000

Data Index: 412327 (The Pile)

Max Activating Token Index: 674

Text #15

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1639143 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1582825 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1552280 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1551373 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 0.7536. Min Range: -0.7536

Max Act: 0.5438. Min Act: -0.0000

Data Index: 740305 (The Pile)

Max Activating Token Index: 848