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

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

Neuron 3505 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: 2.5281. Min Range: -2.5281

Max Act: 2.5281. Min Act: -0.0000

Data Index: 1515994 (Python Code)

Max Activating Token Index: 637

Text #1

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.2622. Min Act: -0.0000

Data Index: 1576613 (Python Code)

Max Activating Token Index: 415

Text #2

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.3821. Min Act: -0.0000

Data Index: 1458111 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.3404. Min Act: -0.0000

Data Index: 281418 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.3448. Min Act: -0.0000

Data Index: 1624094 (Python Code)

Max Activating Token Index: 721

Text #5

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.2961. Min Act: -0.0000

Data Index: 1603682 (Python Code)

Max Activating Token Index: 393

Text #6

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.1253. Min Act: -0.0000

Data Index: 1365609 (Python Code)

Max Activating Token Index: 385

Text #7

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.1295. Min Act: -0.0000

Data Index: 355451 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.2307. Min Act: -0.0000

Data Index: 1426573 (Python Code)

Max Activating Token Index: 938

Text #9

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.1003. Min Act: -0.0000

Data Index: 1554054 (Python Code)

Max Activating Token Index: 1006

Text #10

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.2762. Min Act: -0.0000

Data Index: 1558343 (Python Code)

Max Activating Token Index: 734

Text #11

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.1840. Min Act: -0.0000

Data Index: 1516739 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.3526. Min Act: -0.0000

Data Index: 1369021 (Python Code)

Max Activating Token Index: 1013

Text #13

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9071. Min Act: -0.0000

Data Index: 1423738 (Python Code)

Max Activating Token Index: 1022

Text #14

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.0112. Min Act: -0.0000

Data Index: 1407114 (Python Code)

Max Activating Token Index: 974

Text #15

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.0901. Min Act: -0.0000

Data Index: 1514614 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9771. Min Act: -0.0000

Data Index: 1464567 (Python Code)

Max Activating Token Index: 86

Text #17

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.1080. Min Act: -0.0000

Data Index: 1646162 (Python Code)

Max Activating Token Index: 364

Text #18

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9836. Min Act: -0.0000

Data Index: 1590539 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.0549. Min Act: -0.0000

Data Index: 1582541 (Python Code)

Max Activating Token Index: 326