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

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

Neuron 5556 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0002

Data Index: 401888 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0725. Min Act: -0.0002

Data Index: 539979 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0699. Min Act: -0.0002

Data Index: 627118 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0678. Min Act: -0.0002

Data Index: 905965 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0678. Min Act: -0.0002

Data Index: 541275 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0653. Min Act: -0.0002

Data Index: 673347 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1088268 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0627. Min Act: -0.0002

Data Index: 704118 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0606. Min Act: -0.0002

Data Index: 354760 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0601. Min Act: -0.0002

Data Index: 510110 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0591. Min Act: -0.0002

Data Index: 839134 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0588. Min Act: -0.0002

Data Index: 153377 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0570. Min Act: -0.0002

Data Index: 358281 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0562. Min Act: -0.0002

Data Index: 601691 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0578. Min Act: -0.0002

Data Index: 278227 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0561. Min Act: -0.0002

Data Index: 860466 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1023482 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0570. Min Act: -0.0002

Data Index: 133167 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0545. Min Act: -0.0002

Data Index: 986613 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0551. Min Act: -0.0002

Data Index: 72289 (C4 (Web Text))

Max Activating Token Index: 22