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

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

Neuron 3166 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1277. Min Act: -0.0000

Data Index: 54093 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1025765 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1319886 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1274045 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0717. Min Act: -0.0000

Data Index: 836065 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0716. Min Act: -0.0000

Data Index: 714033 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1354741 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0625. Min Act: -0.0000

Data Index: 864126 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0683. Min Act: -0.0000

Data Index: 551316 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0637. Min Act: -0.0000

Data Index: 525877 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1284317 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0667. Min Act: -0.0000

Data Index: 983627 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0666. Min Act: -0.0000

Data Index: 198770 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0664. Min Act: -0.0000

Data Index: 304363 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1072413 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0664. Min Act: -0.0000

Data Index: 237617 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0640. Min Act: -0.0000

Data Index: 174865 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1053780 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0678. Min Act: -0.0000

Data Index: 578832 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1245132 (C4 (Web Text))

Max Activating Token Index: 393