Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 703 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1455. Min Act: -0.0001

Data Index: 64525 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1582166 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1548943 (Python Code)

Max Activating Token Index: 636

Text #3

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1440464 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1118750 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1475752 (Python Code)

Max Activating Token Index: 862

Text #6

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1365596 (Python Code)

Max Activating Token Index: 508

Text #7

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1077204 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1646294 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0781. Min Act: -0.0000

Data Index: 915578 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0723. Min Act: -0.0001

Data Index: 709895 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0750. Min Act: -0.0001

Data Index: 475359 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0719. Min Act: -0.0000

Data Index: 702064 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1603202 (Python Code)

Max Activating Token Index: 1005

Text #14

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1501465 (Python Code)

Max Activating Token Index: 639

Text #15

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1383725 (Python Code)

Max Activating Token Index: 848

Text #16

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1408611 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0757. Min Act: -0.0001

Data Index: 910459 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0746. Min Act: -0.0000

Data Index: 866410 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1428642 (Python Code)

Max Activating Token Index: 768