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

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

Neuron 4578 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: 0.8701. Min Range: -0.8701

Max Act: 0.8701. Min Act: -0.0000

Data Index: 954585 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.8548. Min Act: -0.0000

Data Index: 224274 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1007019 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6789. Min Act: -0.0000

Data Index: 978807 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.7113. Min Act: -0.0000

Data Index: 139616 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.7316. Min Act: -0.0000

Data Index: 993610 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1004436 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1162337 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6776. Min Act: -0.0000

Data Index: 347092 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1075007 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6501. Min Act: -0.0000

Data Index: 439480 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6529. Min Act: -0.0000

Data Index: 278222 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.5598. Min Act: -0.0000

Data Index: 169898 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6252. Min Act: -0.0000

Data Index: 18393 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1218441 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.5779. Min Act: -0.0000

Data Index: 991736 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1261566 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.5903. Min Act: -0.0000

Data Index: 710799 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.5517. Min Act: -0.0000

Data Index: 531153 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.8701. Min Range: -0.8701

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1174315 (C4 (Web Text))

Max Activating Token Index: 284