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

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

Neuron 817 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4518. Min Range: -3.4518

Max Act: 3.3832. Min Act: -0.0000

Data Index: 1036329 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 3.4518. Min Range: -3.4518

Max Act: 3.3801. Min Act: -0.0000

Data Index: 1101912 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 3.4518. Min Range: -3.4518

Max Act: 3.3640. Min Act: -0.0000

Data Index: 52701 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 3.4518. Min Range: -3.4518

Max Act: 3.1550. Min Act: -0.0000

Data Index: 174186 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.8766. Min Act: -0.0000

Data Index: 1582402 (Python Code)

Max Activating Token Index: 198

Text #5

Max Range: 3.4518. Min Range: -3.4518

Max Act: 3.2754. Min Act: -0.0000

Data Index: 767129 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 3.4518. Min Range: -3.4518

Max Act: 3.2450. Min Act: -0.0000

Data Index: 561221 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 3.4518. Min Range: -3.4518

Max Act: 3.1020. Min Act: -0.0000

Data Index: 352582 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 3.4518. Min Range: -3.4518

Max Act: 3.4518. Min Act: -0.0000

Data Index: 720710 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 3.4518. Min Range: -3.4518

Max Act: 3.1349. Min Act: -0.0000

Data Index: 503746 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.9843. Min Act: -0.0000

Data Index: 1521663 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.4905. Min Act: -0.0000

Data Index: 1551269 (Python Code)

Max Activating Token Index: 377

Text #12

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.9902. Min Act: -0.0000

Data Index: 1510017 (Python Code)

Max Activating Token Index: 696

Text #13

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.9185. Min Act: -0.0000

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.5897. Min Act: -0.0000

Data Index: 1571947 (Python Code)

Max Activating Token Index: 824

Text #15

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.7148. Min Act: -0.0000

Data Index: 1392731 (Python Code)

Max Activating Token Index: 948

Text #16

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.7144. Min Act: -0.0000

Data Index: 1515183 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.5669. Min Act: -0.0000

Data Index: 1416967 (Python Code)

Max Activating Token Index: 584

Text #18

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.5439. Min Act: -0.0000

Data Index: 1184195 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 3.4518. Min Range: -3.4518

Max Act: 2.3713. Min Act: -0.0000

Data Index: 1599379 (Python Code)

Max Activating Token Index: 226