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

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

Neuron 5026 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0596. Min Range: -1.0596

Max Act: 1.0596. Min Act: -0.0001

Data Index: 1207912 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9950. Min Act: -0.0001

Data Index: 157793 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.0596. Min Range: -1.0596

Max Act: 1.0371. Min Act: -0.0001

Data Index: 746240 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 1.0596. Min Range: -1.0596

Max Act: 1.0149. Min Act: -0.0001

Data Index: 388686 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 1.0596. Min Range: -1.0596

Max Act: 1.0275. Min Act: -0.0001

Data Index: 635207 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.0596. Min Range: -1.0596

Max Act: 1.0286. Min Act: -0.0001

Data Index: 643614 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9901. Min Act: -0.0001

Data Index: 645912 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8526. Min Act: -0.0001

Data Index: 1039520 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9201. Min Act: -0.0001

Data Index: 1148701 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9815. Min Act: -0.0001

Data Index: 1312051 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9558. Min Act: -0.0001

Data Index: 915786 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8531. Min Act: -0.0001

Data Index: 662287 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.0596. Min Range: -1.0596

Max Act: 1.0357. Min Act: -0.0001

Data Index: 1027649 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9019. Min Act: -0.0001

Data Index: 264892 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9072. Min Act: -0.0001

Data Index: 256548 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8979. Min Act: -0.0001

Data Index: 650232 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9227. Min Act: -0.0001

Data Index: 1277212 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8494. Min Act: -0.0001

Data Index: 155536 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9147. Min Act: -0.0001

Data Index: 16597 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8827. Min Act: -0.0001

Data Index: 568119 (C4 (Web Text))

Max Activating Token Index: 485