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

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

Neuron 30 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.8069. Min Act: -0.0000

Data Index: 1647090 (Python Code)

Max Activating Token Index: 430

Text #1

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.6268. Min Act: -0.0000

Data Index: 1504883 (Python Code)

Max Activating Token Index: 883

Text #2

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.2093. Min Act: -0.0000

Data Index: 1554468 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.1717. Min Act: -0.0000

Data Index: 1592552 (Python Code)

Max Activating Token Index: 812

Text #4

Max Range: 3.8069. Min Range: -3.8069

Max Act: 3.1428. Min Act: -0.0000

Data Index: 1441227 (Python Code)

Max Activating Token Index: 299

Text #5

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.8990. Min Act: -0.0000

Data Index: 1599640 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.9796. Min Act: -0.0000

Data Index: 1519093 (Python Code)

Max Activating Token Index: 456

Text #7

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.9624. Min Act: -0.0000

Data Index: 1624853 (Python Code)

Max Activating Token Index: 482

Text #8

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.8619. Min Act: -0.0000

Data Index: 1522658 (Python Code)

Max Activating Token Index: 346

Text #9

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.7922. Min Act: -0.0000

Data Index: 1515601 (Python Code)

Max Activating Token Index: 722

Text #10

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.6196. Min Act: -0.0000

Data Index: 1505997 (Python Code)

Max Activating Token Index: 99

Text #11

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.8470. Min Act: -0.0000

Data Index: 1422188 (Python Code)

Max Activating Token Index: 379

Text #12

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.7030. Min Act: -0.0000

Data Index: 1462745 (Python Code)

Max Activating Token Index: 966

Text #13

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.6575. Min Act: -0.0000

Data Index: 1538081 (Python Code)

Max Activating Token Index: 796

Text #14

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.8275. Min Act: -0.0000

Data Index: 1609612 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.5549. Min Act: -0.0000

Data Index: 1481418 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.6745. Min Act: -0.0000

Data Index: 1429187 (Python Code)

Max Activating Token Index: 633

Text #17

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.6219. Min Act: -0.0000

Data Index: 1380230 (Python Code)

Max Activating Token Index: 385

Text #18

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.6353. Min Act: -0.0000

Data Index: 1587327 (Python Code)

Max Activating Token Index: 875

Text #19

Max Range: 3.8069. Min Range: -3.8069

Max Act: 2.6189. Min Act: -0.0000

Data Index: 1376856 (Python Code)

Max Activating Token Index: 380