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

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

Neuron 5153 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.4645. Min Act: -0.0000

Data Index: 614671 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.4260. Min Act: -0.0000

Data Index: 880474 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3968. Min Act: -0.0000

Data Index: 636538 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3605. Min Act: -0.0000

Data Index: 138488 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3606. Min Act: -0.0000

Data Index: 978473 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.4153. Min Act: 0.0000

Data Index: 1489466 (Python Code)

Max Activating Token Index: 812

Text #6

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3608. Min Act: 0.0000

Data Index: 1593367 (Python Code)

Max Activating Token Index: 809

Text #7

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3421. Min Act: -0.0000

Data Index: 684521 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3388. Min Act: -0.0000

Data Index: 599294 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3600. Min Act: 0.0000

Data Index: 1566517 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1176899 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.2895. Min Act: -0.0000

Data Index: 473981 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1255205 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3109. Min Act: -0.0000

Data Index: 341522 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3040. Min Act: -0.0000

Data Index: 342231 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.2975. Min Act: -0.0000

Data Index: 208019 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1553763 (Python Code)

Max Activating Token Index: 548

Text #17

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1006130 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.2794. Min Act: -0.0000

Data Index: 644642 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.4645. Min Range: -0.4645

Max Act: 0.2851. Min Act: -0.0000

Data Index: 412131 (C4 (Web Text))

Max Activating Token Index: 70