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

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

Neuron 2382 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1634868 (Python Code)

Max Activating Token Index: 488

Text #1

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1428677 (Python Code)

Max Activating Token Index: 889

Text #2

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6415. Min Act: -0.0000

Data Index: 410919 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1435865 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1537461 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1653259 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1627870 (Python Code)

Max Activating Token Index: 859

Text #7

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1514107 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1591715 (Python Code)

Max Activating Token Index: 877

Text #9

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4545. Min Act: -0.0000

Data Index: 888457 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4340. Min Act: -0.0000

Data Index: 746121 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4665. Min Act: -0.0000

Data Index: 666978 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4177. Min Act: -0.0000

Data Index: 70844 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4299. Min Act: -0.0000

Data Index: 604686 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1070551 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.3996. Min Act: -0.0000

Data Index: 917444 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4075. Min Act: -0.0000

Data Index: 215989 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.3987. Min Act: -0.0000

Data Index: 907217 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.3793. Min Act: -0.0000

Data Index: 637191 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.3827. Min Act: -0.0000

Data Index: 568531 (C4 (Web Text))

Max Activating Token Index: 38