Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 182 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0003

Data Index: 167924 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0633. Min Act: -0.0003

Data Index: 617124 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1173368 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0612. Min Act: -0.0003

Data Index: 222359 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0589. Min Act: -0.0003

Data Index: 224503 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0586. Min Act: -0.0003

Data Index: 281637 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1094022 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0566. Min Act: -0.0003

Data Index: 648597 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0554. Min Act: -0.0003

Data Index: 76880 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0554. Min Act: -0.0003

Data Index: 192381 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0552. Min Act: -0.0004

Data Index: 137793 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0538. Min Act: -0.0004

Data Index: 800867 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0548. Min Act: -0.0003

Data Index: 715889 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0541. Min Act: -0.0004

Data Index: 877886 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0535. Min Act: -0.0003

Data Index: 961571 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0567. Min Act: -0.0003

Data Index: 742552 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0535. Min Act: -0.0003

Data Index: 533802 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0560. Min Act: -0.0004

Data Index: 110221 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0537. Min Act: -0.0003

Data Index: 659242 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0550. Min Act: -0.0003

Data Index: 84513 (C4 (Web Text))

Max Activating Token Index: 387