Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1727 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0873. Min Act: -0.0002

Data Index: 597241 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0822. Min Act: -0.0001

Data Index: 919685 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0800. Min Act: -0.0001

Data Index: 710793 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1160790 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1131927 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0788. Min Act: -0.0002

Data Index: 500795 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0788. Min Act: -0.0002

Data Index: 332745 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1586537 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1513 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0711. Min Act: -0.0001

Data Index: 74477 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0694. Min Act: -0.0002

Data Index: 758966 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0753. Min Act: -0.0002

Data Index: 858704 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0736. Min Act: -0.0001

Data Index: 561033 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0687. Min Act: -0.0001

Data Index: 851160 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0732. Min Act: -0.0001

Data Index: 556250 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1014482 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0705. Min Act: -0.0001

Data Index: 391687 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1001545 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1177017 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0729. Min Act: -0.0002

Data Index: 706602 (C4 (Web Text))

Max Activating Token Index: 337