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

Dataset: The Pile

Neuron 3595 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: 0.2556. Min Range: -0.2556

Max Act: 0.2556. Min Act: -0.0000

Data Index: 191764 (The Pile)

Max Activating Token Index: 253

Text #1

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2303. Min Act: -0.0000

Data Index: 554520 (The Pile)

Max Activating Token Index: 660

Text #2

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1093185 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2307. Min Act: -0.0000

Data Index: 806306 (The Pile)

Max Activating Token Index: 503

Text #4

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1534698 (The Pile)

Max Activating Token Index: 455

Text #5

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1009454 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1319251 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1943. Min Act: -0.0000

Data Index: 319198 (The Pile)

Max Activating Token Index: 1003

Text #8

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1947138 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1789. Min Act: -0.0000

Data Index: 518294 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1842. Min Act: -0.0000

Data Index: 773352 (The Pile)

Max Activating Token Index: 723

Text #11

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1413700 (The Pile)

Max Activating Token Index: 669

Text #12

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1015976 (The Pile)

Max Activating Token Index: 995

Text #13

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1697. Min Act: -0.0000

Data Index: 282891 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1452. Min Act: -0.0000

Data Index: 126377 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1381085 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1456998 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1321102 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1040944 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1604. Min Act: -0.0000

Data Index: 772220 (The Pile)

Max Activating Token Index: 580