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

Dataset: The Pile

Neuron 1882 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: 1.1063. Min Range: -1.1063

Max Act: 1.1063. Min Act: -0.0000

Data Index: 101509 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0215. Min Act: -0.0000

Data Index: 505924 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1933488 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1518399 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1441677 (The Pile)

Max Activating Token Index: 95

Text #5

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0681. Min Act: -0.0000

Data Index: 832791 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0641. Min Act: -0.0000

Data Index: 350594 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0225. Min Act: -0.0001

Data Index: 644629 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0205. Min Act: -0.0000

Data Index: 1488366 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1453420 (The Pile)

Max Activating Token Index: 563

Text #10

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0086. Min Act: -0.0000

Data Index: 463654 (The Pile)

Max Activating Token Index: 617

Text #11

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0243. Min Act: -0.0000

Data Index: 555903 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1590429 (The Pile)

Max Activating Token Index: 215

Text #13

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1997510 (The Pile)

Max Activating Token Index: 161

Text #14

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1199795 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9782. Min Act: -0.0000

Data Index: 996280 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1986082 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1135529 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9656. Min Act: -0.0000

Data Index: 671897 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9371. Min Act: -0.0000

Data Index: 514847 (The Pile)

Max Activating Token Index: 312