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

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

Neuron 3858 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1451068 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1629299 (Python Code)

Max Activating Token Index: 568

Text #2

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1505340 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1450733 (Python Code)

Max Activating Token Index: 418

Text #4

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1406450 (Python Code)

Max Activating Token Index: 502

Text #5

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0932. Min Act: -0.0000

Data Index: 686006 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1458274 (Python Code)

Max Activating Token Index: 414

Text #7

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1408937 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1441689 (Python Code)

Max Activating Token Index: 221

Text #9

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1120569 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0713. Min Act: -0.0000

Data Index: 1598966 (Python Code)

Max Activating Token Index: 511

Text #11

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1256162 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0667. Min Act: -0.0000

Data Index: 976973 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1369859 (Python Code)

Max Activating Token Index: 695

Text #14

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1457096 (Python Code)

Max Activating Token Index: 438

Text #15

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1632227 (Python Code)

Max Activating Token Index: 899

Text #16

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0604. Min Act: -0.0000

Data Index: 58351 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1453326 (Python Code)

Max Activating Token Index: 76

Text #18

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0606. Min Act: -0.0000

Data Index: 510714 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1529760 (Python Code)

Max Activating Token Index: 573