Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 814 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.1402. Min Range: -2.1402

Max Act: 2.1402. Min Act: -0.0001

Data Index: 1057374 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 2.1402. Min Range: -2.1402

Max Act: 2.0163. Min Act: -0.0001

Data Index: 1213656 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.9867. Min Act: -0.0000

Data Index: 850065 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.9737. Min Act: -0.0001

Data Index: 1155110 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.9697. Min Act: -0.0000

Data Index: 98627 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.9334. Min Act: -0.0000

Data Index: 459483 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.7701. Min Act: -0.0000

Data Index: 1077649 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.5732. Min Act: -0.0000

Data Index: 197627 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.8009. Min Act: -0.0000

Data Index: 439946 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.8587. Min Act: -0.0001

Data Index: 379957 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.7149. Min Act: -0.0001

Data Index: 602957 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.8037. Min Act: -0.0001

Data Index: 62844 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.6124. Min Act: -0.0001

Data Index: 190136 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.5885. Min Act: -0.0000

Data Index: 694611 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.6295. Min Act: -0.0000

Data Index: 584562 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.6533. Min Act: -0.0001

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.6815. Min Act: -0.0001

Data Index: 1195632 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.5475. Min Act: -0.0000

Data Index: 212459 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.4982. Min Act: -0.0001

Data Index: 99699 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 2.1402. Min Range: -2.1402

Max Act: 1.5226. Min Act: -0.0000

Data Index: 481799 (C4 (Web Text))

Max Activating Token Index: 980