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

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

Neuron 3613 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1750. Min Range: -2.1750

Max Act: 2.0524. Min Act: -0.0000

Data Index: 79564 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 2.1750. Min Range: -2.1750

Max Act: 2.1750. Min Act: -0.0000

Data Index: 390909 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.9842. Min Act: -0.0000

Data Index: 1039511 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 2.1750. Min Range: -2.1750

Max Act: 2.0079. Min Act: -0.0000

Data Index: 921360 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.8480. Min Act: -0.0000

Data Index: 438948 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.9151. Min Act: -0.0000

Data Index: 499533 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.9352. Min Act: -0.0000

Data Index: 413296 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.8325. Min Act: -0.0000

Data Index: 85831 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.9374. Min Act: -0.0000

Data Index: 1071607 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.6833. Min Act: -0.0000

Data Index: 292342 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.7342. Min Act: -0.0000

Data Index: 1157402 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.7889. Min Act: -0.0000

Data Index: 734110 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.7822. Min Act: -0.0000

Data Index: 293276 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.6628. Min Act: -0.0000

Data Index: 597844 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.5585. Min Act: 0.0001

Data Index: 702959 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.6721. Min Act: -0.0000

Data Index: 509917 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.5928. Min Act: -0.0000

Data Index: 1936 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.4951. Min Act: -0.0000

Data Index: 1214350 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.6475. Min Act: -0.0000

Data Index: 962921 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 2.1750. Min Range: -2.1750

Max Act: 1.3867. Min Act: -0.0000

Data Index: 190721 (C4 (Web Text))

Max Activating Token Index: 853