Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1773 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1291730 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0003

Data Index: 500216 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0550. Min Act: -0.0004

Data Index: 1349492 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0544. Min Act: -0.0003

Data Index: 652414 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0563. Min Act: -0.0003

Data Index: 603700 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0527. Min Act: -0.0003

Data Index: 70552 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0532. Min Act: -0.0003

Data Index: 584608 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1081734 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0542. Min Act: -0.0003

Data Index: 954264 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0500. Min Act: -0.0003

Data Index: 42020 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0525. Min Act: -0.0004

Data Index: 447251 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0484. Min Act: -0.0002

Data Index: 204837 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1145560 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0494. Min Act: -0.0003

Data Index: 781495 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1053464 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0498. Min Act: -0.0003

Data Index: 332874 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1097794 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0467. Min Act: -0.0003

Data Index: 507364 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0498. Min Act: -0.0002

Data Index: 51848 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0495. Min Act: -0.0003

Data Index: 76673 (C4 (Web Text))

Max Activating Token Index: 432