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

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

Neuron 599 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1345988 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1195585 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.5056. Min Act: -0.0000

Data Index: 304704 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.5347. Min Act: -0.0000

Data Index: 663277 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4910. Min Act: -0.0000

Data Index: 998746 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1256806 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4996. Min Act: -0.0000

Data Index: 438533 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4541. Min Act: -0.0000

Data Index: 16648 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4701. Min Act: -0.0000

Data Index: 411615 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1068197 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1196311 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1198787 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4604. Min Act: -0.0000

Data Index: 493780 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1080821 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1312676 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4238. Min Act: -0.0000

Data Index: 481945 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1346452 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1250886 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4176. Min Act: -0.0000

Data Index: 99953 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1355726 (C4 (Web Text))

Max Activating Token Index: 648