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

Dataset: The Pile

Neuron 472 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: 0.5942. Min Range: -0.5942

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1926704 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1992311 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1770470 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1189444 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5141. Min Act: -0.0000

Data Index: 644158 (The Pile)

Max Activating Token Index: 411

Text #5

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1539897 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5156. Min Act: -0.0000

Data Index: 682075 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5101. Min Act: -0.0000

Data Index: 574610 (The Pile)

Max Activating Token Index: 936

Text #8

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4959. Min Act: -0.0000

Data Index: 608741 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1020579 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1527427 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1188810 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5032. Min Act: -0.0000

Data Index: 567568 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1643919 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1451136 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5070. Min Act: -0.0000

Data Index: 380015 (The Pile)

Max Activating Token Index: 198

Text #16

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1731387 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4419. Min Act: -0.0000

Data Index: 78314 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4353. Min Act: -0.0000

Data Index: 713336 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4515. Min Act: -0.0000

Data Index: 630609 (The Pile)

Max Activating Token Index: 652