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

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

Neuron 4881 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1401. Min Range: -5.1401

Max Act: 5.1401. Min Act: -0.0000

Data Index: 50131 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.5906. Min Act: -0.0001

Data Index: 585793 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 5.1401. Min Range: -5.1401

Max Act: 3.8969. Min Act: -0.0001

Data Index: 421000 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 5.1401. Min Range: -5.1401

Max Act: 3.7538. Min Act: -0.0000

Data Index: 927472 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 5.1401. Min Range: -5.1401

Max Act: 3.6425. Min Act: -0.0000

Data Index: 1245008 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 5.1401. Min Range: -5.1401

Max Act: 3.2860. Min Act: -0.0000

Data Index: 751322 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 5.1401. Min Range: -5.1401

Max Act: 3.3451. Min Act: -0.0001

Data Index: 631811 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 5.1401. Min Range: -5.1401

Max Act: 3.1734. Min Act: -0.0001

Data Index: 1202580 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 5.1401. Min Range: -5.1401

Max Act: 3.0111. Min Act: -0.0001

Data Index: 590493 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 5.1401. Min Range: -5.1401

Max Act: 3.1175. Min Act: -0.0001

Data Index: 844949 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 5.1401. Min Range: -5.1401

Max Act: 3.1368. Min Act: -0.0000

Data Index: 712000 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 5.1401. Min Range: -5.1401

Max Act: 2.7934. Min Act: -0.0000

Data Index: 497619 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 5.1401. Min Range: -5.1401

Max Act: 2.9221. Min Act: -0.0000

Data Index: 801173 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 5.1401. Min Range: -5.1401

Max Act: 2.9067. Min Act: -0.0001

Data Index: 1082712 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 5.1401. Min Range: -5.1401

Max Act: 2.8606. Min Act: -0.0001

Data Index: 404776 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 5.1401. Min Range: -5.1401

Max Act: 2.9342. Min Act: -0.0000

Data Index: 786411 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 5.1401. Min Range: -5.1401

Max Act: 2.6542. Min Act: -0.0000

Data Index: 1246055 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 5.1401. Min Range: -5.1401

Max Act: 2.4374. Min Act: -0.0000

Data Index: 1080336 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 5.1401. Min Range: -5.1401

Max Act: 2.6802. Min Act: -0.0001

Data Index: 486539 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 5.1401. Min Range: -5.1401

Max Act: 2.6851. Min Act: -0.0000

Data Index: 577310 (C4 (Web Text))

Max Activating Token Index: 44