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

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

Neuron 1997 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4442. Min Act: -0.0000

Data Index: 658798 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3896. Min Act: -0.0000

Data Index: 558231 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4050. Min Act: -0.0000

Data Index: 264860 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4391. Min Act: -0.0000

Data Index: 550801 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4430. Min Act: -0.0000

Data Index: 406976 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4494. Min Act: -0.0000

Data Index: 915390 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3938. Min Act: -0.0000

Data Index: 691589 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4373. Min Act: -0.0000

Data Index: 296355 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4331. Min Act: -0.0000

Data Index: 610133 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4252. Min Act: -0.0000

Data Index: 371269 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4117. Min Act: -0.0000

Data Index: 251653 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4143. Min Act: -0.0000

Data Index: 239233 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1337985 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3976. Min Act: -0.0000

Data Index: 91857 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4199. Min Act: -0.0000

Data Index: 571586 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4060. Min Act: -0.0000

Data Index: 478231 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4263. Min Act: -0.0000

Data Index: 299170 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4019. Min Act: -0.0000

Data Index: 20941 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4246. Min Act: -0.0000

Data Index: 942575 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3986. Min Act: -0.0000

Data Index: 369736 (C4 (Web Text))

Max Activating Token Index: 208