Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 927 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0571. Min Act: -0.0003

Data Index: 206089 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0558. Min Act: -0.0003

Data Index: 301069 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0529. Min Act: -0.0003

Data Index: 313580 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1153665 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0525. Min Act: -0.0003

Data Index: 656086 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0519. Min Act: -0.0003

Data Index: 762694 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1029167 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0491. Min Act: -0.0003

Data Index: 746950 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0520. Min Act: -0.0003

Data Index: 518422 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0477. Min Act: -0.0003

Data Index: 941875 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0498. Min Act: -0.0003

Data Index: 952368 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1319809 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0472. Min Act: -0.0003

Data Index: 291244 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0498. Min Act: -0.0003

Data Index: 397123 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0475. Min Act: -0.0003

Data Index: 836607 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1595248 (Python Code)

Max Activating Token Index: 441

Text #16

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0489. Min Act: -0.0003

Data Index: 616203 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0485. Min Act: -0.0003

Data Index: 289116 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1202551 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0473. Min Act: -0.0003

Data Index: 930116 (C4 (Web Text))

Max Activating Token Index: 640