Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1738 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.6215. Min Act: -0.0002

Data Index: 665370 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5757. Min Act: -0.0002

Data Index: 159322 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5878. Min Act: -0.0002

Data Index: 1125225 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.6037. Min Act: -0.0002

Data Index: 751115 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5642. Min Act: -0.0001

Data Index: 90646 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5598. Min Act: -0.0002

Data Index: 954956 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5598. Min Act: -0.0002

Data Index: 949824 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5536. Min Act: -0.0001

Data Index: 1340313 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5735. Min Act: -0.0002

Data Index: 1283065 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5211. Min Act: -0.0002

Data Index: 677982 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5868. Min Act: -0.0001

Data Index: 1095302 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5187. Min Act: -0.0001

Data Index: 222643 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4983. Min Act: -0.0002

Data Index: 847812 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5352. Min Act: -0.0001

Data Index: 722235 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5525. Min Act: -0.0001

Data Index: 416757 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5663. Min Act: -0.0001

Data Index: 66742 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5251. Min Act: -0.0001

Data Index: 684472 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5778. Min Act: -0.0001

Data Index: 794684 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5223. Min Act: -0.0002

Data Index: 188553 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5276. Min Act: -0.0001

Data Index: 867433 (C4 (Web Text))

Max Activating Token Index: 811