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

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

Neuron 675 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.6626. Min Act: -0.0001

Data Index: 108505 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.6086. Min Act: -0.0001

Data Index: 519111 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5301. Min Act: -0.0000

Data Index: 524763 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5373. Min Act: -0.0001

Data Index: 866739 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5392. Min Act: -0.0001

Data Index: 240830 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5535. Min Act: -0.0001

Data Index: 1345375 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4848. Min Act: -0.0001

Data Index: 666737 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5156. Min Act: -0.0001

Data Index: 166948 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5270. Min Act: -0.0001

Data Index: 61193 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5258. Min Act: -0.0001

Data Index: 1184753 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5182. Min Act: -0.0001

Data Index: 326446 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4657. Min Act: -0.0001

Data Index: 371328 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4558. Min Act: -0.0001

Data Index: 351780 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4960. Min Act: -0.0000

Data Index: 14711 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4715. Min Act: -0.0001

Data Index: 577598 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4286. Min Act: -0.0001

Data Index: 830464 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4697. Min Act: -0.0000

Data Index: 870799 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5012. Min Act: -0.0001

Data Index: 1269177 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4642. Min Act: -0.0001

Data Index: 674047 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4481. Min Act: -0.0001

Data Index: 989519 (C4 (Web Text))

Max Activating Token Index: 921