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

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

Neuron 872 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: 0.1087. Min Range: -0.1087

Max Act: 0.0987. Min Act: -0.0002

Data Index: 71925 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.1072. Min Act: -0.0002

Data Index: 12714 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1558063 (Python Code)

Max Activating Token Index: 159

Text #3

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0859. Min Act: -0.0002

Data Index: 524818 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1654089 (Python Code)

Max Activating Token Index: 951

Text #5

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0940. Min Act: -0.0002

Data Index: 74246 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0806. Min Act: -0.0002

Data Index: 329196 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1305693 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1472778 (Python Code)

Max Activating Token Index: 665

Text #9

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0804. Min Act: -0.0002

Data Index: 886824 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0711. Min Act: -0.0002

Data Index: 65671 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0780. Min Act: -0.0002

Data Index: 836258 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1573940 (Python Code)

Max Activating Token Index: 230

Text #13

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0792. Min Act: -0.0002

Data Index: 938307 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1390931 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0737. Min Act: -0.0002

Data Index: 693012 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1611815 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0750. Min Act: -0.0002

Data Index: 510954 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1500263 (Python Code)

Max Activating Token Index: 129

Text #19

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1006521 (C4 (Web Text))

Max Activating Token Index: 669