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

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

Neuron 1649 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8888. Min Act: -0.0000

Data Index: 68380 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5423. Min Act: -0.0000

Data Index: 106713 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5114. Min Act: -0.0000

Data Index: 239606 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4998. Min Act: -0.0000

Data Index: 56978 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1054952 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1040081 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1023461 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4445. Min Act: -0.0000

Data Index: 128617 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4360. Min Act: -0.0000

Data Index: 680070 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4335. Min Act: -0.0000

Data Index: 692349 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4193. Min Act: -0.0000

Data Index: 490759 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1154469 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1005967 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4357. Min Act: -0.0000

Data Index: 244301 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4317. Min Act: -0.0000

Data Index: 460086 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4279. Min Act: -0.0000

Data Index: 499621 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4496. Min Act: -0.0000

Data Index: 449067 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1090277 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4182. Min Act: -0.0000

Data Index: 451191 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.4122. Min Act: -0.0000

Data Index: 843227 (C4 (Web Text))

Max Activating Token Index: 553