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

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

Neuron 574 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: 0.0695. Min Range: -0.0695

Max Act: 0.0695. Min Act: -0.0003

Data Index: 279682 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0628. Min Act: -0.0003

Data Index: 399205 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1242267 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1108288 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0583. Min Act: -0.0003

Data Index: 443666 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0571. Min Act: -0.0003

Data Index: 16992 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1240904 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1341265 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0512. Min Act: -0.0003

Data Index: 361002 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0520. Min Act: -0.0003

Data Index: 387465 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0489. Min Act: -0.0003

Data Index: 473291 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0497. Min Act: -0.0003

Data Index: 93621 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0497. Min Act: -0.0003

Data Index: 228316 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0509. Min Act: -0.0003

Data Index: 351506 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1100436 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0486. Min Act: -0.0003

Data Index: 208655 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0481. Min Act: -0.0003

Data Index: 472945 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0475. Min Act: -0.0002

Data Index: 459126 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0483. Min Act: -0.0003

Data Index: 430993 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1063275 (C4 (Web Text))

Max Activating Token Index: 302