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

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

Neuron 1359 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: 0.0568. Min Range: -0.0568

Max Act: 0.0568. Min Act: -0.0004

Data Index: 706720 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0568. Min Act: -0.0004

Data Index: 232945 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0537. Min Act: -0.0003

Data Index: 82491 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0538. Min Act: -0.0003

Data Index: 708522 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0507. Min Act: -0.0004

Data Index: 507898 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1131403 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0499. Min Act: -0.0003

Data Index: 81360 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0510. Min Act: -0.0003

Data Index: 995512 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0503. Min Act: -0.0003

Data Index: 730456 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0505. Min Act: -0.0003

Data Index: 358797 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0489. Min Act: -0.0004

Data Index: 37330 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0492. Min Act: -0.0004

Data Index: 597746 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0491. Min Act: -0.0003

Data Index: 266201 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0473. Min Act: -0.0004

Data Index: 1168789 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0486. Min Act: -0.0003

Data Index: 90588 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0477. Min Act: -0.0003

Data Index: 322010 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0474. Min Act: -0.0003

Data Index: 811745 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1022480 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0474. Min Act: -0.0004

Data Index: 1002496 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0465. Min Act: -0.0003

Data Index: 541992 (C4 (Web Text))

Max Activating Token Index: 104