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

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

Neuron 2380 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6514. Min Act: -0.0000

Data Index: 1465482 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.3338. Min Act: -0.0000

Data Index: 1435297 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.5211. Min Act: -0.0000

Data Index: 1484289 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.4611. Min Act: -0.0000

Data Index: 1645267 (Python Code)

Max Activating Token Index: 419

Text #4

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.4646. Min Act: 0.0000

Data Index: 1612895 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.7076. Min Act: -0.0000

Data Index: 1458487 (Python Code)

Max Activating Token Index: 478

Text #6

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.4531. Min Act: -0.0000

Data Index: 1450687 (Python Code)

Max Activating Token Index: 590

Text #7

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.1177. Min Act: -0.0000

Data Index: 1375875 (Python Code)

Max Activating Token Index: 246

Text #8

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.1902. Min Act: -0.0000

Data Index: 1465414 (Python Code)

Max Activating Token Index: 323

Text #9

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.1644. Min Act: -0.0000

Data Index: 1529924 (Python Code)

Max Activating Token Index: 910

Text #10

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.0447. Min Act: 0.0000

Data Index: 1486222 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.0512. Min Act: -0.0000

Data Index: 1553497 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.1518. Min Act: 0.0000

Data Index: 1542309 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 3.7076. Min Range: -3.7076

Max Act: 2.6741. Min Act: -0.0000

Data Index: 1630646 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 3.7076. Min Range: -3.7076

Max Act: 2.9018. Min Act: 0.0000

Data Index: 1617354 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 3.7076. Min Range: -3.7076

Max Act: 2.6937. Min Act: -0.0000

Data Index: 1623404 (Python Code)

Max Activating Token Index: 558

Text #16

Max Range: 3.7076. Min Range: -3.7076

Max Act: 2.7316. Min Act: 0.0000

Data Index: 1507104 (Python Code)

Max Activating Token Index: 339

Text #17

Max Range: 3.7076. Min Range: -3.7076

Max Act: 2.8097. Min Act: 0.0000

Data Index: 1438050 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.0593. Min Act: -0.0000

Data Index: 1432326 (Python Code)

Max Activating Token Index: 970

Text #19

Max Range: 3.7076. Min Range: -3.7076

Max Act: 2.6795. Min Act: -0.0000

Data Index: 1469357 (Python Code)

Max Activating Token Index: 733