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

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

Neuron 3761 in Layer 0

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: 1.4565. Min Range: -1.4565

Max Act: 1.4565. Min Act: -0.0001

Data Index: 1273732 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.2606. Min Act: -0.0001

Data Index: 340483 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.2221. Min Act: -0.0001

Data Index: 377050 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.1714. Min Act: -0.0001

Data Index: 823044 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.1425. Min Act: -0.0001

Data Index: 256369 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.1344. Min Act: -0.0001

Data Index: 613546 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.1165. Min Act: -0.0002

Data Index: 547541 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.1192. Min Act: -0.0001

Data Index: 387322 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.1216. Min Act: -0.0002

Data Index: 1108054 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.0642. Min Act: -0.0001

Data Index: 551100 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.0252. Min Act: -0.0001

Data Index: 248307 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.0245. Min Act: -0.0001

Data Index: 894589 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.0097. Min Act: -0.0001

Data Index: 835523 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 1.4565. Min Range: -1.4565

Max Act: 1.0016. Min Act: -0.0001

Data Index: 1341219 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 1.4565. Min Range: -1.4565

Max Act: 0.9827. Min Act: -0.0001

Data Index: 539343 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.4565. Min Range: -1.4565

Max Act: 0.9878. Min Act: -0.0001

Data Index: 590614 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.4565. Min Range: -1.4565

Max Act: 0.9710. Min Act: -0.0001

Data Index: 1086653 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 1.4565. Min Range: -1.4565

Max Act: 0.9643. Min Act: -0.0001

Data Index: 1284602 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 1.4565. Min Range: -1.4565

Max Act: 0.9681. Min Act: -0.0001

Data Index: 566442 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 1.4565. Min Range: -1.4565

Max Act: 0.9601. Min Act: -0.0001

Data Index: 1189268 (C4 (Web Text))

Max Activating Token Index: 1003