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

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

Neuron 3933 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5830. Min Range: -3.5830

Max Act: 3.5830. Min Act: -0.0001

Data Index: 132837 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 3.5830. Min Range: -3.5830

Max Act: 2.9213. Min Act: -0.0001

Data Index: 803326 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 3.5830. Min Range: -3.5830

Max Act: 2.7242. Min Act: -0.0001

Data Index: 1132626 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 3.5830. Min Range: -3.5830

Max Act: 2.1812. Min Act: -0.0001

Data Index: 693903 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 3.5830. Min Range: -3.5830

Max Act: 2.1712. Min Act: -0.0001

Data Index: 616875 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.9386. Min Act: -0.0001

Data Index: 930757 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.9587. Min Act: -0.0001

Data Index: 1202671 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.8497. Min Act: -0.0001

Data Index: 313399 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.8092. Min Act: -0.0001

Data Index: 18732 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.9702. Min Act: -0.0001

Data Index: 416397 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.8185. Min Act: -0.0001

Data Index: 687034 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.8018. Min Act: -0.0001

Data Index: 666224 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.8924. Min Act: -0.0001

Data Index: 513461 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.8189. Min Act: -0.0001

Data Index: 1098083 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.9133. Min Act: -0.0001

Data Index: 1045677 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.8799. Min Act: -0.0001

Data Index: 317906 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.8496. Min Act: -0.0001

Data Index: 980181 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.7339. Min Act: -0.0001

Data Index: 421916 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.8239. Min Act: -0.0001

Data Index: 1111710 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 3.5830. Min Range: -3.5830

Max Act: 1.8409. Min Act: -0.0001

Data Index: 1031641 (C4 (Web Text))

Max Activating Token Index: 908