Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3081 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0746. Min Act: -0.0001

Data Index: 315103 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0550. Min Act: -0.0002

Data Index: 494265 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0615. Min Act: -0.0002

Data Index: 369686 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1316980 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0582. Min Act: -0.0001

Data Index: 847649 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0560. Min Act: -0.0001

Data Index: 977270 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1157662 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0602. Min Act: -0.0001

Data Index: 400245 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0584. Min Act: -0.0002

Data Index: 528410 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0558. Min Act: -0.0001

Data Index: 354743 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0571. Min Act: -0.0002

Data Index: 390056 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1340884 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1261236 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1272079 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0568. Min Act: -0.0001

Data Index: 504799 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0511. Min Act: -0.0001

Data Index: 187936 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1124478 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0559. Min Act: -0.0001

Data Index: 700727 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0582. Min Act: -0.0001

Data Index: 245659 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0547. Min Act: -0.0001

Data Index: 280525 (C4 (Web Text))

Max Activating Token Index: 556