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

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

Neuron 4036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0555. Min Range: -1.0555

Max Act: 1.0555. Min Act: -0.0000

Data Index: 997287 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1268771 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1164467 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1190815 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.4975. Min Act: -0.0000

Data Index: 618619 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.4449. Min Act: -0.0000

Data Index: 695612 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.4117. Min Act: -0.0000

Data Index: 846528 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3792. Min Act: -0.0000

Data Index: 240762 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.4068. Min Act: -0.0000

Data Index: 779584 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.4118. Min Act: -0.0000

Data Index: 258712 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3503. Min Act: -0.0000

Data Index: 20225 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3734. Min Act: -0.0000

Data Index: 457475 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3438. Min Act: -0.0000

Data Index: 84859 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3259. Min Act: -0.0000

Data Index: 918069 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3691. Min Act: -0.0000

Data Index: 398604 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1276107 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3409. Min Act: -0.0001

Data Index: 409444 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3199. Min Act: -0.0000

Data Index: 740714 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3305. Min Act: -0.0000

Data Index: 237392 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1296590 (C4 (Web Text))

Max Activating Token Index: 747