Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 362 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0002

Data Index: 340504 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0599. Min Act: -0.0002

Data Index: 184536 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1130458 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0576. Min Act: -0.0002

Data Index: 936963 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1272048 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0568. Min Act: -0.0002

Data Index: 984759 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0576. Min Act: -0.0002

Data Index: 225488 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1047163 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0579. Min Act: -0.0002

Data Index: 657447 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0566. Min Act: -0.0002

Data Index: 648364 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0556. Min Act: -0.0002

Data Index: 602685 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0556. Min Act: -0.0002

Data Index: 698109 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0548. Min Act: -0.0002

Data Index: 683685 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1035161 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0561. Min Act: -0.0002

Data Index: 83444 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0555. Min Act: -0.0002

Data Index: 763780 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0562. Min Act: -0.0002

Data Index: 422255 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0543. Min Act: -0.0002

Data Index: 598922 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0561. Min Act: -0.0002

Data Index: 264946 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1033774 (C4 (Web Text))

Max Activating Token Index: 483