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

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

Neuron 4817 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0899. Min Range: -1.0899

Max Act: 1.0100. Min Act: -0.0001

Data Index: 573239 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.0899. Min Range: -1.0899

Max Act: 1.0899. Min Act: -0.0001

Data Index: 296022 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9064. Min Act: -0.0001

Data Index: 1090256 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9593. Min Act: -0.0001

Data Index: 432862 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9172. Min Act: -0.0001

Data Index: 986749 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9507. Min Act: -0.0001

Data Index: 106910 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8352. Min Act: -0.0001

Data Index: 795211 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8812. Min Act: -0.0001

Data Index: 1244672 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8258. Min Act: -0.0001

Data Index: 1308658 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8445. Min Act: -0.0001

Data Index: 1273197 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8894. Min Act: -0.0001

Data Index: 93327 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7978. Min Act: -0.0001

Data Index: 421505 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7665. Min Act: -0.0001

Data Index: 1398 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8221. Min Act: -0.0001

Data Index: 337338 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8185. Min Act: -0.0001

Data Index: 462478 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7662. Min Act: -0.0001

Data Index: 388621 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8061. Min Act: -0.0001

Data Index: 643848 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7773. Min Act: -0.0001

Data Index: 1098387 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7571. Min Act: -0.0001

Data Index: 870304 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7698. Min Act: -0.0001

Data Index: 479903 (C4 (Web Text))

Max Activating Token Index: 639