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

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

Neuron 672 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3702. Min Act: -0.0000

Data Index: 1058730 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.1560. Min Act: -0.0000

Data Index: 743625 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.2132. Min Act: -0.0000

Data Index: 538475 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.0434. Min Act: -0.0000

Data Index: 435497 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.0781. Min Act: -0.0000

Data Index: 1071212 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.1048. Min Act: -0.0000

Data Index: 96128 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.1105. Min Act: -0.0000

Data Index: 20237 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.9664. Min Act: -0.0000

Data Index: 795147 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.9308. Min Act: -0.0000

Data Index: 106498 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.9754. Min Act: -0.0000

Data Index: 772806 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.9103. Min Act: -0.0000

Data Index: 284561 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.8142. Min Act: -0.0000

Data Index: 912452 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.8499. Min Act: -0.0000

Data Index: 766970 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.9343. Min Act: -0.0000

Data Index: 259986 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.9017. Min Act: -0.0000

Data Index: 576998 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1187514 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.9592. Min Act: -0.0000

Data Index: 46224 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.8739. Min Act: -0.0000

Data Index: 563866 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.9332. Min Act: -0.0000

Data Index: 335024 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.3702. Min Range: -1.3702

Max Act: 0.9260. Min Act: -0.0000

Data Index: 893783 (C4 (Web Text))

Max Activating Token Index: 585