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

Dataset: The Pile

Neuron 4084 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1243687 (The Pile)

Max Activating Token Index: 158

Text #1

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.5243. Min Act: -0.0000

Data Index: 691679 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1884110 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1402896 (The Pile)

Max Activating Token Index: 983

Text #4

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.3940. Min Act: -0.0000

Data Index: 875415 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1362254 (The Pile)

Max Activating Token Index: 709

Text #6

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4531. Min Act: -0.0000

Data Index: 148818 (The Pile)

Max Activating Token Index: 681

Text #7

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4068. Min Act: -0.0000

Data Index: 588002 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4224. Min Act: -0.0000

Data Index: 535673 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4154. Min Act: -0.0000

Data Index: 156344 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4232. Min Act: -0.0000

Data Index: 286916 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4172. Min Act: -0.0000

Data Index: 777240 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1344968 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1340994 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1635679 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1447773 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4245. Min Act: -0.0000

Data Index: 730451 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4004. Min Act: -0.0000

Data Index: 800586 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4037. Min Act: -0.0000

Data Index: 375874 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1305310 (The Pile)

Max Activating Token Index: 549