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

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

Neuron 3493 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: 1.0541. Min Range: -1.0541

Max Act: 1.0541. Min Act: -0.0000

Data Index: 384582 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.9986. Min Act: -0.0000

Data Index: 1262059 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.9339. Min Act: -0.0000

Data Index: 835503 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1169189 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.9189. Min Act: -0.0000

Data Index: 796976 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.8401. Min Act: -0.0000

Data Index: 815280 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.9280. Min Act: -0.0000

Data Index: 899909 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.8172. Min Act: -0.0000

Data Index: 872769 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.9019. Min Act: -0.0000

Data Index: 356851 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1215408 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.8251. Min Act: -0.0000

Data Index: 948365 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.7616. Min Act: -0.0000

Data Index: 474122 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.8520. Min Act: -0.0000

Data Index: 945665 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.7744. Min Act: -0.0000

Data Index: 544026 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1235152 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.7608. Min Act: -0.0000

Data Index: 276779 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.7849. Min Act: -0.0000

Data Index: 1259234 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.7815. Min Act: -0.0001

Data Index: 187513 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.7510. Min Act: -0.0000

Data Index: 690997 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 1.0541. Min Range: -1.0541

Max Act: 0.7686. Min Act: -0.0000

Data Index: 928499 (C4 (Web Text))

Max Activating Token Index: 636