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

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

Neuron 3350 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1198. Min Range: -3.1198

Max Act: 3.1198. Min Act: -0.0001

Data Index: 149374 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 3.1198. Min Range: -3.1198

Max Act: 3.1022. Min Act: -0.0000

Data Index: 742619 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.7920. Min Act: -0.0001

Data Index: 745507 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.5979. Min Act: -0.0000

Data Index: 1339787 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.3026. Min Act: -0.0001

Data Index: 900891 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.4931. Min Act: -0.0001

Data Index: 667699 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.1935. Min Act: -0.0001

Data Index: 1225822 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.2795. Min Act: -0.0001

Data Index: 1020637 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.2571. Min Act: -0.0001

Data Index: 870914 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.2233. Min Act: -0.0001

Data Index: 180729 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.0883. Min Act: -0.0001

Data Index: 1326605 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.1950. Min Act: -0.0000

Data Index: 383534 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 3.1198. Min Range: -3.1198

Max Act: 1.9440. Min Act: -0.0000

Data Index: 654355 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.2544. Min Act: -0.0000

Data Index: 1283498 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 3.1198. Min Range: -3.1198

Max Act: 1.4820. Min Act: -0.0000

Data Index: 1247264 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 3.1198. Min Range: -3.1198

Max Act: 2.1446. Min Act: -0.0000

Data Index: 614582 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 3.1198. Min Range: -3.1198

Max Act: 1.9922. Min Act: -0.0001

Data Index: 1050084 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 3.1198. Min Range: -3.1198

Max Act: 1.9990. Min Act: -0.0001

Data Index: 393217 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 3.1198. Min Range: -3.1198

Max Act: 1.9817. Min Act: -0.0001

Data Index: 301169 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 3.1198. Min Range: -3.1198

Max Act: 1.8540. Min Act: -0.0000

Data Index: 518853 (C4 (Web Text))

Max Activating Token Index: 859