Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3824. Min Act: -0.0001

Data Index: 1110163 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3363. Min Act: -0.0001

Data Index: 747225 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3576. Min Act: -0.0001

Data Index: 566928 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3077. Min Act: -0.0001

Data Index: 638844 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3136. Min Act: -0.0001

Data Index: 366722 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3361. Min Act: -0.0001

Data Index: 852027 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3239. Min Act: -0.0001

Data Index: 1081862 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1300008 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3119. Min Act: -0.0001

Data Index: 10911 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2995. Min Act: -0.0001

Data Index: 360401 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2703. Min Act: -0.0001

Data Index: 1219686 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2714. Min Act: -0.0001

Data Index: 212769 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2671. Min Act: -0.0001

Data Index: 1138659 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2606. Min Act: -0.0001

Data Index: 292998 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2625. Min Act: -0.0001

Data Index: 780597 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2677. Min Act: -0.0001

Data Index: 1068311 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2507. Min Act: -0.0001

Data Index: 1000976 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2545. Min Act: -0.0001

Data Index: 37091 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2559. Min Act: -0.0001

Data Index: 350153 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2498. Min Act: -0.0001

Data Index: 887676 (C4 (Web Text))

Max Activating Token Index: 341