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

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

Neuron 1063 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.6788. Min Act: -0.0000

Data Index: 916891 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.5915. Min Act: -0.0000

Data Index: 289647 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.4837. Min Act: -0.0000

Data Index: 551025 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.3099. Min Act: -0.0000

Data Index: 53195 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.3881. Min Act: -0.0000

Data Index: 1156834 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.2135. Min Act: -0.0000

Data Index: 302377 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.2332. Min Act: -0.0000

Data Index: 1153005 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.2627. Min Act: -0.0000

Data Index: 1269576 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0622. Min Act: -0.0000

Data Index: 466623 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0712. Min Act: -0.0000

Data Index: 722387 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0635. Min Act: -0.0000

Data Index: 315921 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 2.6788. Min Range: -2.6788

Max Act: 1.9589. Min Act: -0.0000

Data Index: 569266 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0523. Min Act: -0.0000

Data Index: 296088 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0353. Min Act: -0.0000

Data Index: 583655 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0392. Min Act: -0.0000

Data Index: 1257004 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0005. Min Act: -0.0000

Data Index: 876242 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 2.6788. Min Range: -2.6788

Max Act: 2.0953. Min Act: -0.0000

Data Index: 1302778 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 2.6788. Min Range: -2.6788

Max Act: 1.9777. Min Act: -0.0000

Data Index: 970718 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 2.6788. Min Range: -2.6788

Max Act: 1.9757. Min Act: -0.0000

Data Index: 1277172 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 2.6788. Min Range: -2.6788

Max Act: 1.9675. Min Act: -0.0000

Data Index: 715082 (C4 (Web Text))

Max Activating Token Index: 940