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

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

Neuron 4702 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.6234. Min Act: -0.0000

Data Index: 450983 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1140455 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5487. Min Act: -0.0000

Data Index: 479678 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.4528. Min Act: -0.0000

Data Index: 984981 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.3910. Min Act: -0.0000

Data Index: 322067 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1210454 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2955. Min Act: -0.0000

Data Index: 607873 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2915. Min Act: -0.0000

Data Index: 368043 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2716. Min Act: -0.0000

Data Index: 368356 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2637. Min Act: -0.0000

Data Index: 929087 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2804. Min Act: -0.0000

Data Index: 175374 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2511. Min Act: -0.0000

Data Index: 797951 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1023809 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2429. Min Act: -0.0000

Data Index: 883911 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2216. Min Act: -0.0000

Data Index: 176008 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2443. Min Act: -0.0000

Data Index: 949726 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1225247 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2135. Min Act: -0.0000

Data Index: 681704 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1175830 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1095747 (C4 (Web Text))

Max Activating Token Index: 634