Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2437 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7918. Min Act: -0.0000

Data Index: 909170 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1935768 (The Pile)

Max Activating Token Index: 504

Text #2

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1231995 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1856757 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7172. Min Act: -0.0000

Data Index: 716344 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1807981 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6304. Min Act: -0.0000

Data Index: 389491 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7151. Min Act: -0.0000

Data Index: 373173 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6518. Min Act: -0.0000

Data Index: 932594 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6496. Min Act: -0.0000

Data Index: 281629 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6953. Min Act: -0.0000

Data Index: 460817 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6793. Min Act: -0.0000

Data Index: 607763 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6944. Min Act: -0.0000

Data Index: 222404 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1551557 (The Pile)

Max Activating Token Index: 275

Text #14

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1787331 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1517567 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1888108 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6249. Min Act: -0.0000

Data Index: 419933 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6248. Min Act: -0.0000

Data Index: 747637 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6348. Min Act: -0.0000

Data Index: 624707 (The Pile)

Max Activating Token Index: 775