Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1750 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0702. Min Act: -0.0002

Data Index: 29913 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1540201 (Python Code)

Max Activating Token Index: 259

Text #2

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0619. Min Act: -0.0002

Data Index: 444186 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0615. Min Act: -0.0002

Data Index: 934055 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0614. Min Act: -0.0002

Data Index: 429770 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0621. Min Act: -0.0002

Data Index: 684597 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1386442 (Python Code)

Max Activating Token Index: 408

Text #7

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1473724 (Python Code)

Max Activating Token Index: 148

Text #8

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0565. Min Act: -0.0002

Data Index: 133574 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0600. Min Act: -0.0002

Data Index: 260598 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0571. Min Act: -0.0002

Data Index: 654428 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0540. Min Act: -0.0002

Data Index: 848428 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1511508 (Python Code)

Max Activating Token Index: 362

Text #13

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0544. Min Act: -0.0002

Data Index: 954912 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0511. Min Act: -0.0002

Data Index: 592862 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1618271 (Python Code)

Max Activating Token Index: 200

Text #16

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0496. Min Act: -0.0002

Data Index: 102718 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1042522 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0506. Min Act: -0.0002

Data Index: 841228 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0486. Min Act: -0.0002

Data Index: 949615 (C4 (Web Text))

Max Activating Token Index: 19