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

Dataset: The Pile

Neuron 357 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: 0.5476. Min Range: -0.5476

Max Act: 0.5476. Min Act: -0.0000

Data Index: 250086 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4835. Min Act: -0.0000

Data Index: 501076 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4812. Min Act: -0.0000

Data Index: 548912 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4488. Min Act: -0.0000

Data Index: 754688 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4609. Min Act: -0.0000

Data Index: 539668 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4338. Min Act: -0.0000

Data Index: 449200 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1637202 (The Pile)

Max Activating Token Index: 685

Text #7

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1398778 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4314. Min Act: -0.0000

Data Index: 416453 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4421. Min Act: -0.0000

Data Index: 732587 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4412. Min Act: -0.0000

Data Index: 359708 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4245. Min Act: -0.0001

Data Index: 1139666 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1459953 (The Pile)

Max Activating Token Index: 680

Text #13

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1982847 (The Pile)

Max Activating Token Index: 751

Text #14

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4185. Min Act: -0.0000

Data Index: 710314 (The Pile)

Max Activating Token Index: 535

Text #15

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4252. Min Act: -0.0000

Data Index: 121868 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4156. Min Act: -0.0000

Data Index: 40409 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1263065 (The Pile)

Max Activating Token Index: 714

Text #18

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1140809 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 0.5476. Min Range: -0.5476

Max Act: 0.4197. Min Act: -0.0000

Data Index: 184172 (The Pile)

Max Activating Token Index: 415