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

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

Neuron 3374 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7402. Min Act: -0.0001

Data Index: 1416828 (Python Code)

Max Activating Token Index: 623

Text #1

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7097. Min Act: -0.0002

Data Index: 669677 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6631. Min Act: -0.0002

Data Index: 770174 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7023. Min Act: -0.0001

Data Index: 1572402 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7008. Min Act: -0.0002

Data Index: 281331 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6697. Min Act: -0.0001

Data Index: 1655789 (Python Code)

Max Activating Token Index: 893

Text #6

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6462. Min Act: -0.0001

Data Index: 1589928 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7480. Min Act: -0.0001

Data Index: 441744 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6750. Min Act: -0.0001

Data Index: 1610695 (Python Code)

Max Activating Token Index: 938

Text #9

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6267. Min Act: -0.0002

Data Index: 1191334 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6403. Min Act: -0.0002

Data Index: 120154 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6045. Min Act: -0.0001

Data Index: 1446113 (Python Code)

Max Activating Token Index: 808

Text #12

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.7140. Min Act: -0.0001

Data Index: 384235 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6189. Min Act: -0.0002

Data Index: 1097760 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6373. Min Act: -0.0001

Data Index: 1643762 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6142. Min Act: -0.0001

Data Index: 1627216 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6082. Min Act: -0.0001

Data Index: 1635349 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.5793. Min Act: -0.0001

Data Index: 1538736 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.6092. Min Act: -0.0001

Data Index: 1428843 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 0.7480. Min Range: -0.7480

Max Act: 0.5836. Min Act: -0.0001

Data Index: 1482357 (Python Code)

Max Activating Token Index: 889