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

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

Neuron 351 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2968. Min Act: -0.0000

Data Index: 495078 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2590. Min Act: -0.0000

Data Index: 486489 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1117956 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2343. Min Act: -0.0000

Data Index: 530091 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2375. Min Act: -0.0000

Data Index: 757450 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2284. Min Act: -0.0000

Data Index: 568035 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2071. Min Act: -0.0000

Data Index: 377872 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2122. Min Act: -0.0000

Data Index: 980611 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1233047 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1166991 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2119. Min Act: -0.0000

Data Index: 963477 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1771. Min Act: -0.0000

Data Index: 672604 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1877. Min Act: -0.0000

Data Index: 120810 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1163832 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1057164 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1039451 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1675. Min Act: -0.0000

Data Index: 670424 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1203869 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1230645 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1237126 (C4 (Web Text))

Max Activating Token Index: 283