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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4973 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.5043. Min Act: -0.0000

Data Index: 171143 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2254. Min Act: -0.0000

Data Index: 331869 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2042. Min Act: -0.0000

Data Index: 166371 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1265068 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1081871 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.1684. Min Act: -0.0000

Data Index: 584712 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.1032. Min Act: -0.0000

Data Index: 3862 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.1259. Min Act: -0.0000

Data Index: 1012581 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 1.5043. Min Range: -1.5043

Max Act: 0.9908. Min Act: -0.0000

Data Index: 5855 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.0781. Min Act: -0.0000

Data Index: 6 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.0110. Min Act: -0.0000

Data Index: 794127 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.1293. Min Act: -0.0000

Data Index: 946392 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.0335. Min Act: -0.0000

Data Index: 718418 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.0229. Min Act: -0.0000

Data Index: 88475 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.1538. Min Act: -0.0000

Data Index: 690121 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.0841. Min Act: -0.0000

Data Index: 26150 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1195456 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.5043. Min Range: -1.5043

Max Act: 0.9990. Min Act: -0.0000

Data Index: 263405 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.0774. Min Act: -0.0000

Data Index: 150236 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 1.5043. Min Range: -1.5043

Max Act: 1.1055. Min Act: -0.0000

Data Index: 168649 (C4 (Web Text))

Max Activating Token Index: 37