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

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

Neuron 5692 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: 2.2509. Min Range: -2.2509

Max Act: 2.2509. Min Act: -0.0000

Data Index: 1001937 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.8476. Min Act: -0.0000

Data Index: 967869 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.8783. Min Act: -0.0000

Data Index: 414302 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.6383. Min Act: -0.0000

Data Index: 1279659 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.8100. Min Act: -0.0000

Data Index: 353663 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.7980. Min Act: -0.0000

Data Index: 1309624 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.6178. Min Act: -0.0000

Data Index: 284193 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.3628. Min Act: -0.0000

Data Index: 326684 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.5536. Min Act: -0.0000

Data Index: 784590 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.8177. Min Act: -0.0000

Data Index: 581429 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.5244. Min Act: -0.0000

Data Index: 929629 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.6126. Min Act: -0.0000

Data Index: 84733 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.6056. Min Act: -0.0000

Data Index: 868460 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.6680. Min Act: -0.0000

Data Index: 94562 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.7303. Min Act: -0.0000

Data Index: 287341 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.3200. Min Act: -0.0000

Data Index: 611645 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.2709. Min Act: -0.0000

Data Index: 630010 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.3661. Min Act: -0.0000

Data Index: 179719 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.4463. Min Act: -0.0000

Data Index: 1325084 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 2.2509. Min Range: -2.2509

Max Act: 1.5665. Min Act: -0.0000

Data Index: 86824 (C4 (Web Text))

Max Activating Token Index: 241