Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1431 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1268372 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0544. Min Act: -0.0002

Data Index: 928699 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0558. Min Act: -0.0002

Data Index: 598290 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1039307 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0505. Min Act: -0.0002

Data Index: 648503 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0553. Min Act: -0.0002

Data Index: 547819 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1261931 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0512. Min Act: -0.0002

Data Index: 975330 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0551. Min Act: -0.0002

Data Index: 715771 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0475. Min Act: -0.0002

Data Index: 50563 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0499. Min Act: -0.0002

Data Index: 942434 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0473. Min Act: -0.0002

Data Index: 302722 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0481. Min Act: -0.0002

Data Index: 802131 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0477. Min Act: -0.0002

Data Index: 894017 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0512. Min Act: -0.0002

Data Index: 430553 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0492. Min Act: -0.0002

Data Index: 674387 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1095550 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0466. Min Act: -0.0002

Data Index: 952945 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1228491 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0492. Min Act: -0.0002

Data Index: 245618 (C4 (Web Text))

Max Activating Token Index: 575