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

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

Neuron 5336 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: 0.0652. Min Range: -0.0652

Max Act: 0.0632. Min Act: -0.0002

Data Index: 368493 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0002

Data Index: 305249 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0609. Min Act: -0.0002

Data Index: 329278 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1277223 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0560. Min Act: -0.0002

Data Index: 762833 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1304124 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1110040 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0542. Min Act: -0.0002

Data Index: 278746 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0576. Min Act: -0.0002

Data Index: 641622 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0553. Min Act: -0.0002

Data Index: 337642 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1198115 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0534. Min Act: -0.0002

Data Index: 186872 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0508. Min Act: -0.0002

Data Index: 646454 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1291130 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0544. Min Act: -0.0002

Data Index: 885839 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1117791 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1105797 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0509. Min Act: -0.0002

Data Index: 922305 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1331642 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1289890 (C4 (Web Text))

Max Activating Token Index: 195