Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1124 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1738. Min Act: -0.0002

Data Index: 643196 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1705. Min Act: -0.0002

Data Index: 529117 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1547. Min Act: -0.0002

Data Index: 855795 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1627. Min Act: -0.0002

Data Index: 576064 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1592. Min Act: -0.0002

Data Index: 1064709 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1562. Min Act: -0.0002

Data Index: 433929 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1555. Min Act: -0.0002

Data Index: 50301 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1509. Min Act: -0.0002

Data Index: 791975 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1644. Min Act: -0.0002

Data Index: 648170 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1547. Min Act: -0.0002

Data Index: 725176 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1581. Min Act: -0.0002

Data Index: 191412 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1555. Min Act: -0.0002

Data Index: 851018 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1455. Min Act: -0.0002

Data Index: 138055 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1543. Min Act: -0.0002

Data Index: 940561 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1383. Min Act: -0.0002

Data Index: 94850 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1445. Min Act: -0.0002

Data Index: 1018521 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1443. Min Act: -0.0002

Data Index: 1194286 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1464. Min Act: -0.0002

Data Index: 966167 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1447. Min Act: -0.0002

Data Index: 203143 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1507. Min Act: -0.0002

Data Index: 1016818 (C4 (Web Text))

Max Activating Token Index: 604