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

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

Neuron 2789 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3809. Min Act: -0.0002

Data Index: 330622 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3299. Min Act: -0.0002

Data Index: 614183 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3270. Min Act: -0.0002

Data Index: 117221 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3058. Min Act: -0.0002

Data Index: 250776 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2724. Min Act: -0.0002

Data Index: 646646 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2707. Min Act: -0.0002

Data Index: 142863 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2597. Min Act: -0.0002

Data Index: 569375 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2577. Min Act: -0.0002

Data Index: 1035173 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2542. Min Act: -0.0002

Data Index: 1272797 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2494. Min Act: -0.0002

Data Index: 487865 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2474. Min Act: -0.0002

Data Index: 846873 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2373. Min Act: -0.0002

Data Index: 33504 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2430. Min Act: -0.0002

Data Index: 33138 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2408. Min Act: -0.0002

Data Index: 442890 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2500. Min Act: -0.0002

Data Index: 863405 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2560. Min Act: -0.0002

Data Index: 80629 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2499. Min Act: -0.0002

Data Index: 1259919 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2384. Min Act: -0.0002

Data Index: 139117 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2456. Min Act: -0.0002

Data Index: 1090007 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2367. Min Act: -0.0002

Data Index: 1183183 (C4 (Web Text))

Max Activating Token Index: 86