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

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

Neuron 2874 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: 0.2648. Min Range: -0.2648

Max Act: 0.2648. Min Act: -0.0001

Data Index: 998571 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1726. Min Act: -0.0001

Data Index: 886821 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1710. Min Act: -0.0001

Data Index: 20079 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1124459 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1276107 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1660. Min Act: -0.0001

Data Index: 35140 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1471. Min Act: -0.0001

Data Index: 408483 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1596. Min Act: -0.0001

Data Index: 492725 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1521854 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1525. Min Act: -0.0001

Data Index: 668274 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1489. Min Act: -0.0001

Data Index: 936007 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1313. Min Act: -0.0001

Data Index: 693404 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1312. Min Act: -0.0001

Data Index: 285966 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1157263 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1396. Min Act: -0.0001

Data Index: 124615 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1338. Min Act: -0.0001

Data Index: 32706 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1421. Min Act: -0.0001

Data Index: 497113 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1301783 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1400. Min Act: -0.0001

Data Index: 1120007 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1311. Min Act: -0.0001

Data Index: 578023 (C4 (Web Text))

Max Activating Token Index: 1006