Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3168 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6377. Min Act: -0.0001

Data Index: 1513378 (Python Code)

Max Activating Token Index: 108

Text #1

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6212. Min Act: -0.0001

Data Index: 1330268 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6550. Min Act: -0.0001

Data Index: 1542394 (Python Code)

Max Activating Token Index: 243

Text #3

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6072. Min Act: -0.0001

Data Index: 1461514 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6032. Min Act: -0.0001

Data Index: 23039 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5791. Min Act: -0.0001

Data Index: 1480885 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5591. Min Act: -0.0001

Data Index: 1520003 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5701. Min Act: -0.0002

Data Index: 356679 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5192. Min Act: -0.0001

Data Index: 1595751 (Python Code)

Max Activating Token Index: 575

Text #9

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5959. Min Act: -0.0001

Data Index: 1433680 (Python Code)

Max Activating Token Index: 284

Text #10

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5744. Min Act: -0.0001

Data Index: 1373868 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5479. Min Act: -0.0001

Data Index: 1574328 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5602. Min Act: -0.0002

Data Index: 559599 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5410. Min Act: -0.0002

Data Index: 486862 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5531. Min Act: -0.0002

Data Index: 866028 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5548. Min Act: -0.0002

Data Index: 1219879 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5550. Min Act: -0.0002

Data Index: 389640 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5477. Min Act: -0.0002

Data Index: 1332810 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5511. Min Act: -0.0001

Data Index: 499665 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5270. Min Act: -0.0002

Data Index: 1291581 (C4 (Web Text))

Max Activating Token Index: 532