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

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

Neuron 3572 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1197. Min Range: -2.1197

Max Act: 2.1197. Min Act: -0.0000

Data Index: 551581 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9022. Min Act: -0.0000

Data Index: 240959 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9507. Min Act: -0.0000

Data Index: 253505 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9429. Min Act: -0.0000

Data Index: 822647 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.8729. Min Act: -0.0000

Data Index: 599185 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9317. Min Act: -0.0000

Data Index: 1169836 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9187. Min Act: -0.0000

Data Index: 126278 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9159. Min Act: -0.0000

Data Index: 1049403 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9077. Min Act: -0.0000

Data Index: 1150808 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9099. Min Act: -0.0000

Data Index: 429445 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9026. Min Act: -0.0000

Data Index: 248330 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.8486. Min Act: -0.0000

Data Index: 721137 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.8996. Min Act: -0.0000

Data Index: 1338840 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.8918. Min Act: -0.0000

Data Index: 473310 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.8818. Min Act: -0.0000

Data Index: 417240 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.8364. Min Act: -0.0000

Data Index: 1320444 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9328. Min Act: -0.0000

Data Index: 283156 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.8261. Min Act: -0.0000

Data Index: 1251659 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.9704. Min Act: -0.0000

Data Index: 1048345 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 2.1197. Min Range: -2.1197

Max Act: 1.8676. Min Act: -0.0000

Data Index: 1006552 (C4 (Web Text))

Max Activating Token Index: 866