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

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

Neuron 3635 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4865. Min Act: -0.0000

Data Index: 644367 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1234848 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3671. Min Act: -0.0000

Data Index: 999682 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1071768 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3828. Min Act: -0.0000

Data Index: 695788 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3779. Min Act: -0.0000

Data Index: 447888 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3858. Min Act: -0.0000

Data Index: 775875 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3371. Min Act: -0.0001

Data Index: 706174 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1224360 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3712. Min Act: -0.0000

Data Index: 580694 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1171948 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3446. Min Act: -0.0000

Data Index: 498325 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3620. Min Act: -0.0001

Data Index: 1257757 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3616. Min Act: -0.0000

Data Index: 499856 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3514. Min Act: -0.0001

Data Index: 507453 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3473. Min Act: -0.0000

Data Index: 606284 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3546. Min Act: -0.0000

Data Index: 334464 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3477. Min Act: -0.0000

Data Index: 93339 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3491. Min Act: -0.0000

Data Index: 473334 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3397. Min Act: -0.0000

Data Index: 707995 (C4 (Web Text))

Max Activating Token Index: 259