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

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

Neuron 2845 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.5482. Min Act: -0.0000

Data Index: 470316 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.3621. Min Act: -0.0000

Data Index: 201176 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2982. Min Act: -0.0000

Data Index: 851452 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1286468 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2709. Min Act: -0.0000

Data Index: 751984 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2941. Min Act: -0.0000

Data Index: 753115 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2717. Min Act: -0.0000

Data Index: 345453 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1192007 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2746. Min Act: -0.0000

Data Index: 244420 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2611. Min Act: -0.0000

Data Index: 985102 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1215919 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1280560 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2367. Min Act: -0.0000

Data Index: 396967 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2562. Min Act: -0.0000

Data Index: 468553 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2468. Min Act: -0.0000

Data Index: 131620 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2531. Min Act: -0.0000

Data Index: 215280 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2375. Min Act: -0.0000

Data Index: 240958 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1180593 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1052005 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.2280. Min Act: -0.0000

Data Index: 227907 (C4 (Web Text))

Max Activating Token Index: 872