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

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

Neuron 1704 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: 0.9525. Min Range: -0.9525

Max Act: 0.9525. Min Act: -0.0001

Data Index: 75140 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8984. Min Act: -0.0001

Data Index: 969959 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8737. Min Act: -0.0001

Data Index: 461945 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8319. Min Act: -0.0001

Data Index: 1047686 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8223. Min Act: -0.0001

Data Index: 499477 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8110. Min Act: -0.0001

Data Index: 168061 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8359. Min Act: -0.0001

Data Index: 404670 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7849. Min Act: -0.0002

Data Index: 388048 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7756. Min Act: -0.0001

Data Index: 300424 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7690. Min Act: -0.0001

Data Index: 414122 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7781. Min Act: -0.0001

Data Index: 1240058 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7660. Min Act: -0.0001

Data Index: 1001065 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7742. Min Act: -0.0001

Data Index: 1135653 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7624. Min Act: -0.0001

Data Index: 230692 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7675. Min Act: -0.0001

Data Index: 527086 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7407. Min Act: -0.0002

Data Index: 915722 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7383. Min Act: -0.0001

Data Index: 170934 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7538. Min Act: -0.0001

Data Index: 288024 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7442. Min Act: -0.0001

Data Index: 1225815 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7355. Min Act: -0.0001

Data Index: 1150264 (C4 (Web Text))

Max Activating Token Index: 238