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

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

Neuron 2049 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.1386. Min Act: -0.0001

Data Index: 469816 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8992. Min Act: -0.0001

Data Index: 1079348 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8127. Min Act: -0.0001

Data Index: 77449 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8002. Min Act: -0.0001

Data Index: 1054663 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.6847. Min Act: -0.0001

Data Index: 1359603 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.7172. Min Act: -0.0001

Data Index: 1072267 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.6911. Min Act: -0.0001

Data Index: 318360 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.6614. Min Act: -0.0001

Data Index: 1198209 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.6019. Min Act: -0.0000

Data Index: 97195 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.6280. Min Act: -0.0001

Data Index: 523436 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.5981. Min Act: -0.0001

Data Index: 679785 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.5764. Min Act: -0.0001

Data Index: 1164891 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.5908. Min Act: -0.0001

Data Index: 1317185 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.5481. Min Act: -0.0001

Data Index: 874713 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.5798. Min Act: -0.0001

Data Index: 952597 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.5463. Min Act: -0.0001

Data Index: 398252 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.5813. Min Act: -0.0001

Data Index: 558543 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.5576. Min Act: -0.0001

Data Index: 1339477 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.4566. Min Act: -0.0001

Data Index: 534820 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.5619. Min Act: -0.0001

Data Index: 865248 (C4 (Web Text))

Max Activating Token Index: 784