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

Dataset: The Pile

Neuron 2819 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: 1.1116. Min Range: -1.1116

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1674562 (The Pile)

Max Activating Token Index: 376

Text #1

Max Range: 1.1116. Min Range: -1.1116

Max Act: 1.0671. Min Act: -0.0000

Data Index: 423977 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 1.1116. Min Range: -1.1116

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1693480 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1672006 (The Pile)

Max Activating Token Index: 31

Text #4

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.7668. Min Act: -0.0000

Data Index: 1339677 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.7859. Min Act: -0.0000

Data Index: 418371 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1456342 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1059142 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.6362. Min Act: -0.0000

Data Index: 598197 (The Pile)

Max Activating Token Index: 295

Text #9

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.7205. Min Act: -0.0000

Data Index: 203512 (The Pile)

Max Activating Token Index: 441

Text #10

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.6785. Min Act: -0.0000

Data Index: 189230 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1455641 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1372423 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1235989 (The Pile)

Max Activating Token Index: 429

Text #14

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1475686 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.5258. Min Act: -0.0000

Data Index: 804187 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.6458. Min Act: -0.0000

Data Index: 428921 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1482370 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1007828 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 1.1116. Min Range: -1.1116

Max Act: 0.5160. Min Act: -0.0000

Data Index: 220000 (The Pile)

Max Activating Token Index: 409