Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5238 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.4808. Min Act: -0.0000

Data Index: 786098 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.3785. Min Act: -0.0000

Data Index: 69703 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.3176. Min Act: -0.0000

Data Index: 482376 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1314345 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1081300 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.1812. Min Act: -0.0000

Data Index: 346129 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.2211. Min Act: -0.0000

Data Index: 151126 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.1512. Min Act: -0.0000

Data Index: 11951 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.1322. Min Act: -0.0000

Data Index: 363683 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.2164. Min Act: -0.0000

Data Index: 376962 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.1358. Min Act: -0.0000

Data Index: 169129 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.0359. Min Act: -0.0000

Data Index: 669782 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.1303. Min Act: -0.0000

Data Index: 434126 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.0770. Min Act: -0.0000

Data Index: 266889 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.9847. Min Act: -0.0000

Data Index: 349274 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.1047. Min Act: -0.0000

Data Index: 237511 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.0325. Min Act: -0.0000

Data Index: 976198 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.4808. Min Range: -1.4808

Max Act: 1.0204. Min Act: -0.0000

Data Index: 374578 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.9862. Min Act: -0.0000

Data Index: 133958 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 1.4808. Min Range: -1.4808

Max Act: 0.9815. Min Act: -0.0000

Data Index: 742703 (C4 (Web Text))

Max Activating Token Index: 669