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

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

Neuron 2563 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1350721 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.7101. Min Act: -0.0000

Data Index: 741490 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6727. Min Act: -0.0000

Data Index: 914959 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6761. Min Act: -0.0000

Data Index: 847422 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6184. Min Act: -0.0000

Data Index: 5321 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6364. Min Act: -0.0000

Data Index: 149285 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5912. Min Act: -0.0000

Data Index: 557503 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5941. Min Act: -0.0000

Data Index: 227135 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6143. Min Act: -0.0000

Data Index: 218482 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5877. Min Act: 0.0000

Data Index: 259978 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1045922 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1314674 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1158515 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1096430 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1236396 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5505. Min Act: -0.0000

Data Index: 873003 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5226. Min Act: -0.0000

Data Index: 688776 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5196. Min Act: -0.0000

Data Index: 666311 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5516. Min Act: -0.0000

Data Index: 738645 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5344. Min Act: 0.0000

Data Index: 900668 (C4 (Web Text))

Max Activating Token Index: 195