Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5606 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 18.2690. Min Range: -18.2690

Max Act: 18.2629. Min Act: -0.0002

Data Index: 665579 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 18.2690. Min Range: -18.2690

Max Act: 18.2690. Min Act: -0.0002

Data Index: 88918 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.9091. Min Act: -0.0002

Data Index: 1272195 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.9093. Min Act: -0.0002

Data Index: 146325 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 18.2690. Min Range: -18.2690

Max Act: 18.0368. Min Act: -0.0002

Data Index: 329905 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 18.2690. Min Range: -18.2690

Max Act: 18.0331. Min Act: -0.0002

Data Index: 1338274 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 18.2690. Min Range: -18.2690

Max Act: 18.0280. Min Act: -0.0002

Data Index: 817982 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 18.2690. Min Range: -18.2690

Max Act: 18.0251. Min Act: -0.0002

Data Index: 342070 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 18.2690. Min Range: -18.2690

Max Act: 18.0235. Min Act: -0.0002

Data Index: 1359437 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.8893. Min Act: -0.0002

Data Index: 888335 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 18.2690. Min Range: -18.2690

Max Act: 18.0049. Min Act: -0.0002

Data Index: 1232481 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.9603. Min Act: -0.0002

Data Index: 667478 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.9358. Min Act: -0.0002

Data Index: 83621 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.9326. Min Act: -0.0002

Data Index: 37702 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.7821. Min Act: -0.0002

Data Index: 356842 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.9219. Min Act: -0.0002

Data Index: 1348559 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.9090. Min Act: -0.0002

Data Index: 936070 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.7739. Min Act: -0.0002

Data Index: 571358 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.7896. Min Act: -0.0002

Data Index: 917692 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 18.2690. Min Range: -18.2690

Max Act: 17.9087. Min Act: -0.0002

Data Index: 795876 (C4 (Web Text))

Max Activating Token Index: 252