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

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

Neuron 4474 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: 0.0716. Min Range: -0.0716

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1356279 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0675. Min Act: -0.0002

Data Index: 571912 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0663. Min Act: -0.0002

Data Index: 851239 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0647. Min Act: -0.0002

Data Index: 109814 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0617. Min Act: -0.0002

Data Index: 660440 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0591. Min Act: -0.0002

Data Index: 67917 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1339500 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0560. Min Act: -0.0002

Data Index: 71601 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1158956 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1235548 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0517. Min Act: -0.0002

Data Index: 747031 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0532. Min Act: -0.0002

Data Index: 790514 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1297548 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1033783 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1244665 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1306952 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0512. Min Act: -0.0002

Data Index: 211140 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0490. Min Act: -0.0002

Data Index: 193352 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0499. Min Act: -0.0002

Data Index: 660692 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0494. Min Act: -0.0002

Data Index: 264839 (C4 (Web Text))

Max Activating Token Index: 192