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

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

Neuron 2083 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0636. Min Act: -0.0003

Data Index: 725460 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0627. Min Act: -0.0003

Data Index: 728367 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0003

Data Index: 65651 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0644. Min Act: -0.0003

Data Index: 841724 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1220209 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0576. Min Act: -0.0003

Data Index: 823596 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1274323 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0638. Min Act: -0.0003

Data Index: 979080 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1161657 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0604. Min Act: -0.0003

Data Index: 137856 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0581. Min Act: -0.0003

Data Index: 411555 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0589. Min Act: -0.0003

Data Index: 769618 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0641. Min Act: -0.0003

Data Index: 519126 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0602. Min Act: -0.0003

Data Index: 158648 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0603. Min Act: -0.0003

Data Index: 259440 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0627. Min Act: -0.0003

Data Index: 625912 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0589. Min Act: -0.0003

Data Index: 492550 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0600. Min Act: -0.0003

Data Index: 375203 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0587. Min Act: -0.0003

Data Index: 105281 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0595. Min Act: -0.0003

Data Index: 458591 (C4 (Web Text))

Max Activating Token Index: 231