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

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

Neuron 4976 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1375709 (Python Code)

Max Activating Token Index: 482

Text #1

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1653526 (Python Code)

Max Activating Token Index: 437

Text #2

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1625620 (Python Code)

Max Activating Token Index: 434

Text #3

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1525389 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5429. Min Act: -0.0000

Data Index: 590354 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1403375 (Python Code)

Max Activating Token Index: 274

Text #6

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5286. Min Act: -0.0000

Data Index: 372073 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1656047 (Python Code)

Max Activating Token Index: 240

Text #8

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1624888 (Python Code)

Max Activating Token Index: 363

Text #9

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1387466 (Python Code)

Max Activating Token Index: 689

Text #10

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1465526 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1437627 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1498881 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5101. Min Act: -0.0000

Data Index: 620868 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1387915 (Python Code)

Max Activating Token Index: 876

Text #15

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4435. Min Act: -0.0000

Data Index: 206234 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4224. Min Act: -0.0000

Data Index: 1140900 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1574844 (Python Code)

Max Activating Token Index: 790

Text #18

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1589171 (Python Code)

Max Activating Token Index: 1018

Text #19

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1577978 (Python Code)

Max Activating Token Index: 628