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

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

Neuron 480 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0376. Min Range: -1.0376

Max Act: 1.0376. Min Act: -0.0001

Data Index: 504064 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.9107. Min Act: -0.0001

Data Index: 929475 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7953. Min Act: -0.0001

Data Index: 342281 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7591. Min Act: -0.0001

Data Index: 1279661 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7547. Min Act: -0.0001

Data Index: 147226 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7453. Min Act: -0.0001

Data Index: 803640 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6707. Min Act: -0.0001

Data Index: 505740 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7111. Min Act: -0.0001

Data Index: 864436 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6741. Min Act: -0.0001

Data Index: 482760 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6702. Min Act: -0.0001

Data Index: 896687 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6945. Min Act: -0.0001

Data Index: 1111784 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6606. Min Act: -0.0001

Data Index: 73791 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6224. Min Act: -0.0001

Data Index: 1029020 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6546. Min Act: -0.0001

Data Index: 607491 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6609. Min Act: -0.0001

Data Index: 1004667 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1253398 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6558. Min Act: -0.0001

Data Index: 563324 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7137. Min Act: -0.0001

Data Index: 1091 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6477. Min Act: -0.0001

Data Index: 336953 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6696. Min Act: -0.0001

Data Index: 798034 (C4 (Web Text))

Max Activating Token Index: 340