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

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

Neuron 3210 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0537. Min Act: -0.0003

Data Index: 707034 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0003

Data Index: 72222 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0528. Min Act: -0.0003

Data Index: 984016 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1102940 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0528. Min Act: -0.0003

Data Index: 1147146 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1121220 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1284979 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0507. Min Act: -0.0003

Data Index: 383938 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0527. Min Act: -0.0003

Data Index: 271461 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0503. Min Act: -0.0003

Data Index: 296599 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1188178 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0501. Min Act: -0.0003

Data Index: 352120 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0507. Min Act: -0.0003

Data Index: 256851 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0511. Min Act: -0.0003

Data Index: 490987 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0504. Min Act: -0.0003

Data Index: 367759 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1103170 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0506. Min Act: -0.0003

Data Index: 479915 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0493. Min Act: -0.0003

Data Index: 892623 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0485. Min Act: -0.0003

Data Index: 52219 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0492. Min Act: -0.0003

Data Index: 547629 (C4 (Web Text))

Max Activating Token Index: 475