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

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

Neuron 4166 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.4716. Min Act: -0.0000

Data Index: 1505009 (Python Code)

Max Activating Token Index: 1015

Text #1

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3237. Min Act: -0.0000

Data Index: 1629299 (Python Code)

Max Activating Token Index: 939

Text #2

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3749. Min Act: -0.0000

Data Index: 1377086 (Python Code)

Max Activating Token Index: 829

Text #3

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.4177. Min Act: -0.0000

Data Index: 1401048 (Python Code)

Max Activating Token Index: 912

Text #4

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1498486 (Python Code)

Max Activating Token Index: 1001

Text #5

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.1838. Min Act: -0.0000

Data Index: 255766 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.1890. Min Act: -0.0000

Data Index: 1653988 (Python Code)

Max Activating Token Index: 76

Text #7

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.3639. Min Act: -0.0000

Data Index: 1636142 (Python Code)

Max Activating Token Index: 816

Text #8

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1304039 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1443848 (Python Code)

Max Activating Token Index: 772

Text #10

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1454148 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.0005. Min Act: -0.0000

Data Index: 570316 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 1.4716. Min Range: -1.4716

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1594005 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 1.4716. Min Range: -1.4716

Max Act: 0.9759. Min Act: -0.0000

Data Index: 426723 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 1.4716. Min Range: -1.4716

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1419925 (Python Code)

Max Activating Token Index: 741

Text #15

Max Range: 1.4716. Min Range: -1.4716

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1472530 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 1.4716. Min Range: -1.4716

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1541973 (Python Code)

Max Activating Token Index: 558

Text #17

Max Range: 1.4716. Min Range: -1.4716

Max Act: 0.8872. Min Act: -0.0000

Data Index: 281368 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.4716. Min Range: -1.4716

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1490776 (Python Code)

Max Activating Token Index: 847

Text #19

Max Range: 1.4716. Min Range: -1.4716

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1408002 (Python Code)

Max Activating Token Index: 565