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

Dataset: The Pile

Neuron 2504 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: 0.7140. Min Range: -0.7140

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1222965 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1035182 (The Pile)

Max Activating Token Index: 267

Text #2

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6873. Min Act: -0.0000

Data Index: 86865 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6467. Min Act: -0.0000

Data Index: 144779 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1042243 (The Pile)

Max Activating Token Index: 401

Text #5

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1870963 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6172. Min Act: -0.0000

Data Index: 510353 (The Pile)

Max Activating Token Index: 358

Text #7

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6097. Min Act: -0.0000

Data Index: 49417 (The Pile)

Max Activating Token Index: 418

Text #8

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1823922 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6198. Min Act: -0.0000

Data Index: 332199 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1495607 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5732. Min Act: -0.0000

Data Index: 304428 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1630665 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1076758 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1127840 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1906315 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1847336 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5214. Min Act: -0.0000

Data Index: 685241 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5141. Min Act: -0.0000

Data Index: 715088 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1562032 (The Pile)

Max Activating Token Index: 393