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

Dataset: The Pile

Neuron 614 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: 1.1086. Min Range: -1.1086

Max Act: 1.1086. Min Act: -0.0000

Data Index: 731214 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1845911 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9126. Min Act: -0.0000

Data Index: 4410 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1843293 (The Pile)

Max Activating Token Index: 97

Text #4

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8909. Min Act: -0.0000

Data Index: 809682 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1420123 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7449. Min Act: -0.0000

Data Index: 927665 (The Pile)

Max Activating Token Index: 693

Text #7

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1896669 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1185470 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1524191 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7035. Min Act: -0.0000

Data Index: 493590 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1543553 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7078. Min Act: -0.0000

Data Index: 853388 (The Pile)

Max Activating Token Index: 619

Text #13

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.6822. Min Act: -0.0000

Data Index: 270166 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1591428 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1892462 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1750639 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1498893 (The Pile)

Max Activating Token Index: 197

Text #18

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1554133 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7188. Min Act: 0.0000

Data Index: 1878771 (The Pile)

Max Activating Token Index: 265