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

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

Neuron 4653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.9032. Min Act: -0.0000

Data Index: 342791 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.7260. Min Act: -0.0000

Data Index: 827523 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.7293. Min Act: -0.0000

Data Index: 351306 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.6868. Min Act: -0.0000

Data Index: 674170 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5950. Min Act: -0.0000

Data Index: 745898 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.6099. Min Act: -0.0000

Data Index: 485841 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5940. Min Act: -0.0000

Data Index: 375400 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5702. Min Act: -0.0000

Data Index: 738570 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1290349 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5478. Min Act: -0.0000

Data Index: 952983 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5479. Min Act: -0.0000

Data Index: 385750 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5429. Min Act: -0.0000

Data Index: 808239 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5406. Min Act: -0.0000

Data Index: 718050 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1030529 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5186. Min Act: -0.0000

Data Index: 691319 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5348. Min Act: -0.0000

Data Index: 959726 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1304023 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5179. Min Act: -0.0000

Data Index: 917653 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5167. Min Act: -0.0000

Data Index: 45495 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5109. Min Act: -0.0000

Data Index: 748669 (C4 (Web Text))

Max Activating Token Index: 911