Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4446 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.6638. Min Act: -0.0000

Data Index: 815612 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5547. Min Act: -0.0000

Data Index: 556525 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.5124. Min Act: -0.0000

Data Index: 974461 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4958. Min Act: -0.0000

Data Index: 348002 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1227394 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4476. Min Act: -0.0000

Data Index: 92402 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4429. Min Act: -0.0000

Data Index: 958932 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.4199. Min Act: -0.0000

Data Index: 922509 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1318669 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3779. Min Act: 0.0000

Data Index: 1231853 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3645. Min Act: -0.0000

Data Index: 500723 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3586. Min Act: -0.0000

Data Index: 357443 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1293862 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3752. Min Act: -0.0000

Data Index: 835814 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3593. Min Act: -0.0000

Data Index: 711399 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3569. Min Act: -0.0000

Data Index: 310858 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3643. Min Act: -0.0000

Data Index: 659374 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3481. Min Act: -0.0000

Data Index: 702284 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3436. Min Act: -0.0000

Data Index: 524809 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.6638. Min Range: -0.6638

Max Act: 0.3409. Min Act: -0.0000

Data Index: 363620 (C4 (Web Text))

Max Activating Token Index: 118