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

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

Neuron 4527 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.8150. Min Act: -0.0000

Data Index: 738823 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.9047. Min Act: -0.0000

Data Index: 886589 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7212. Min Act: -0.0000

Data Index: 876179 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7131. Min Act: -0.0000

Data Index: 112251 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5817. Min Act: -0.0000

Data Index: 147781 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7513. Min Act: -0.0000

Data Index: 908732 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.4892. Min Act: -0.0000

Data Index: 682639 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5846. Min Act: -0.0000

Data Index: 380418 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.3048. Min Act: -0.0000

Data Index: 970387 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6775. Min Act: -0.0000

Data Index: 1094073 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6821. Min Act: -0.0000

Data Index: 848259 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.4663. Min Act: -0.0000

Data Index: 30778 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5352. Min Act: -0.0000

Data Index: 877224 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.3946. Min Act: -0.0000

Data Index: 64710 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.3591. Min Act: -0.0000

Data Index: 413226 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.3163. Min Act: -0.0000

Data Index: 569371 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.3424. Min Act: -0.0000

Data Index: 139347 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1122093 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2132. Min Act: -0.0000

Data Index: 50859 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2032. Min Act: -0.0000

Data Index: 452783 (C4 (Web Text))

Max Activating Token Index: 1008