Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 9 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2625. Min Act: -0.0001

Data Index: 920053 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2323. Min Act: -0.0001

Data Index: 344325 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1293904 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1986. Min Act: -0.0001

Data Index: 290131 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1972. Min Act: -0.0001

Data Index: 166232 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1274934 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1902. Min Act: -0.0001

Data Index: 337290 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1756. Min Act: -0.0001

Data Index: 1158972 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1783. Min Act: -0.0001

Data Index: 182380 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1852. Min Act: -0.0001

Data Index: 1163702 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1835. Min Act: -0.0001

Data Index: 766903 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1751. Min Act: -0.0001

Data Index: 332587 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1861. Min Act: -0.0001

Data Index: 793814 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1601. Min Act: -0.0001

Data Index: 675824 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1728. Min Act: -0.0001

Data Index: 392916 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1587. Min Act: -0.0001

Data Index: 73408 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1695. Min Act: -0.0001

Data Index: 537163 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1564. Min Act: -0.0001

Data Index: 584791 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1529. Min Act: -0.0001

Data Index: 302720 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1475. Min Act: -0.0001

Data Index: 506048 (C4 (Web Text))

Max Activating Token Index: 976