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

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

Neuron 596 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: 0.5265. Min Range: -0.5265

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1009087 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.5265. Min Act: -0.0000

Data Index: 734538 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4687. Min Act: -0.0000

Data Index: 349138 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4763. Min Act: -0.0000

Data Index: 586626 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4737. Min Act: -0.0000

Data Index: 19327 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1225072 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4838. Min Act: -0.0000

Data Index: 492995 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4438. Min Act: -0.0000

Data Index: 486938 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1243305 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4442. Min Act: -0.0000

Data Index: 952763 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4373. Min Act: -0.0000

Data Index: 214422 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4182. Min Act: -0.0000

Data Index: 518194 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4262. Min Act: -0.0000

Data Index: 691154 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4107. Min Act: -0.0000

Data Index: 235343 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4266. Min Act: -0.0000

Data Index: 398066 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4013. Min Act: -0.0000

Data Index: 593688 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.3945. Min Act: -0.0000

Data Index: 635686 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1293926 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1197125 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1261298 (C4 (Web Text))

Max Activating Token Index: 160