Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1352 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1142. Min Act: -0.0000

Data Index: 230009 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0999. Min Act: -0.0000

Data Index: 231053 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0962. Min Act: -0.0000

Data Index: 111431 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0880. Min Act: -0.0000

Data Index: 465867 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0988. Min Act: -0.0000

Data Index: 751411 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1469155 (Python Code)

Max Activating Token Index: 979

Text #6

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0959. Min Act: -0.0000

Data Index: 395967 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0890. Min Act: -0.0000

Data Index: 646772 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0850. Min Act: -0.0000

Data Index: 288632 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0939. Min Act: -0.0000

Data Index: 293598 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0835. Min Act: -0.0000

Data Index: 812336 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0847. Min Act: -0.0000

Data Index: 198437 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1220646 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1614703 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0817. Min Act: -0.0000

Data Index: 177706 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0849. Min Act: -0.0000

Data Index: 475178 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0848. Min Act: -0.0000

Data Index: 803014 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0831. Min Act: -0.0000

Data Index: 7467 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0831. Min Act: -0.0000

Data Index: 343542 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0797. Min Act: -0.0000

Data Index: 56289 (C4 (Web Text))

Max Activating Token Index: 50