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

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

Neuron 1072 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0789. Min Act: -0.0004

Data Index: 1128288 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0660. Min Act: -0.0004

Data Index: 733619 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0683. Min Act: -0.0004

Data Index: 233705 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0667. Min Act: -0.0004

Data Index: 257301 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0610. Min Act: -0.0004

Data Index: 776176 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0519. Min Act: -0.0004

Data Index: 1314718 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0558. Min Act: -0.0004

Data Index: 1265595 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0529. Min Act: -0.0004

Data Index: 399113 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0505. Min Act: -0.0004

Data Index: 646225 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0546. Min Act: -0.0004

Data Index: 1114961 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0465. Min Act: -0.0004

Data Index: 50905 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0515. Min Act: -0.0004

Data Index: 1131925 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0513. Min Act: -0.0004

Data Index: 799692 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0518. Min Act: -0.0004

Data Index: 420927 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0514. Min Act: -0.0004

Data Index: 768133 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0507. Min Act: -0.0004

Data Index: 1175122 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0450. Min Act: -0.0004

Data Index: 633517 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0470. Min Act: -0.0004

Data Index: 311827 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0441. Min Act: -0.0004

Data Index: 950438 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0458. Min Act: -0.0004

Data Index: 815317 (C4 (Web Text))

Max Activating Token Index: 337