Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1986 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.5432. Min Act: -0.0000

Data Index: 329400 (The Pile)

Max Activating Token Index: 298

Text #1

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.5124. Min Act: -0.0000

Data Index: 611033 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.5076. Min Act: -0.0001

Data Index: 80354 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.5127. Min Act: 0.0000

Data Index: 753312 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4681. Min Act: 0.0001

Data Index: 129058 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1910180 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4572. Min Act: -0.0000

Data Index: 774854 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1198641 (The Pile)

Max Activating Token Index: 481

Text #8

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1356670 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4166. Min Act: -0.0000

Data Index: 971408 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1648143 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4366. Min Act: -0.0001

Data Index: 1384262 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4353. Min Act: 0.0000

Data Index: 1626520 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1421546 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4249. Min Act: -0.0001

Data Index: 1964416 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4260. Min Act: -0.0001

Data Index: 741780 (The Pile)

Max Activating Token Index: 545

Text #16

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4107. Min Act: 0.0000

Data Index: 1864164 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4213. Min Act: -0.0001

Data Index: 709398 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4330. Min Act: -0.0000

Data Index: 304737 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1495853 (The Pile)

Max Activating Token Index: 731