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

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

Neuron 763 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: 0.9194. Min Range: -0.9194

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1035719 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8043. Min Act: -0.0000

Data Index: 621465 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1206215 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.6226. Min Act: -0.0000

Data Index: 172822 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1557338 (Python Code)

Max Activating Token Index: 593

Text #5

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.5262. Min Act: -0.0000

Data Index: 31609 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.5697. Min Act: -0.0000

Data Index: 904740 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.5420. Min Act: -0.0000

Data Index: 79730 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.5865. Min Act: -0.0000

Data Index: 228269 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.4632. Min Act: -0.0000

Data Index: 510990 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1266406 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.5466. Min Act: -0.0000

Data Index: 8909 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.4610. Min Act: -0.0000

Data Index: 566646 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1247860 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.4733. Min Act: -0.0000

Data Index: 166755 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.5006. Min Act: -0.0000

Data Index: 359959 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.4902. Min Act: -0.0000

Data Index: 167267 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.4652. Min Act: -0.0000

Data Index: 169683 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.4827. Min Act: -0.0000

Data Index: 257723 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.4283. Min Act: -0.0000

Data Index: 763305 (C4 (Web Text))

Max Activating Token Index: 781