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

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

Neuron 2725 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2175. Min Act: -0.0000

Data Index: 454364 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2032. Min Act: -0.0000

Data Index: 126389 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1937. Min Act: -0.0000

Data Index: 502812 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1979. Min Act: -0.0000

Data Index: 764593 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1901. Min Act: -0.0000

Data Index: 716856 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1140626 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1763. Min Act: -0.0000

Data Index: 740243 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1643. Min Act: -0.0000

Data Index: 229816 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1688. Min Act: -0.0000

Data Index: 861823 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1600. Min Act: -0.0000

Data Index: 506452 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1108884 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1628. Min Act: -0.0000

Data Index: 157849 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1646. Min Act: -0.0000

Data Index: 882324 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1525. Min Act: -0.0000

Data Index: 376792 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1071694 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1498. Min Act: -0.0000

Data Index: 68098 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1112219 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1487. Min Act: -0.0000

Data Index: 938666 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1464. Min Act: -0.0000

Data Index: 984057 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1460. Min Act: -0.0000

Data Index: 7463 (C4 (Web Text))

Max Activating Token Index: 331