Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1620 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.8070. Min Act: -0.0003

Data Index: 115708 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.8168. Min Act: -0.0002

Data Index: 697955 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.8114. Min Act: -0.0003

Data Index: 80014 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7911. Min Act: -0.0002

Data Index: 920318 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.8040. Min Act: -0.0002

Data Index: 529691 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.8034. Min Act: -0.0003

Data Index: 1336364 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7796. Min Act: -0.0002

Data Index: 1149015 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7760. Min Act: -0.0002

Data Index: 951453 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7971. Min Act: -0.0003

Data Index: 587871 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7934. Min Act: -0.0002

Data Index: 1116797 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7726. Min Act: -0.0002

Data Index: 901511 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7849. Min Act: -0.0003

Data Index: 738247 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7865. Min Act: -0.0002

Data Index: 475886 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7693. Min Act: -0.0002

Data Index: 925672 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7767. Min Act: -0.0002

Data Index: 937973 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7834. Min Act: -0.0002

Data Index: 1129310 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7775. Min Act: -0.0002

Data Index: 626718 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7665. Min Act: -0.0002

Data Index: 529422 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7590. Min Act: -0.0002

Data Index: 265877 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7731. Min Act: -0.0002

Data Index: 608041 (C4 (Web Text))

Max Activating Token Index: 664