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

Dataset: The Pile

Neuron 922 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1363979 (The Pile)

Max Activating Token Index: 937

Text #1

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.5068. Min Act: -0.0000

Data Index: 70315 (The Pile)

Max Activating Token Index: 467

Text #2

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1569644 (The Pile)

Max Activating Token Index: 594

Text #3

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1936552 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1265960 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1826159 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1612869 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4757. Min Act: -0.0000

Data Index: 803997 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4407. Min Act: -0.0000

Data Index: 921611 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1672284 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4626. Min Act: -0.0000

Data Index: 9061 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1302716 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4588. Min Act: -0.0000

Data Index: 209063 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1015539 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4379. Min Act: -0.0000

Data Index: 461721 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4468. Min Act: -0.0000

Data Index: 378987 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1889502 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1369527 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4345. Min Act: -0.0000

Data Index: 459175 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4504. Min Act: -0.0000

Data Index: 343857 (The Pile)

Max Activating Token Index: 429