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

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

Neuron 609 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0648. Min Act: -0.0002

Data Index: 1639534 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9931. Min Act: -0.0002

Data Index: 1604956 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1411278 (Python Code)

Max Activating Token Index: 715

Text #3

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8579. Min Act: -0.0002

Data Index: 1518687 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8403. Min Act: -0.0002

Data Index: 1331303 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8568. Min Act: -0.0002

Data Index: 1540061 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8543. Min Act: -0.0002

Data Index: 1423921 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8736. Min Act: -0.0002

Data Index: 1431923 (Python Code)

Max Activating Token Index: 445

Text #8

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8659. Min Act: -0.0002

Data Index: 1512109 (Python Code)

Max Activating Token Index: 506

Text #9

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8184. Min Act: -0.0002

Data Index: 1478678 (Python Code)

Max Activating Token Index: 467

Text #10

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8191. Min Act: -0.0002

Data Index: 1636901 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8096. Min Act: -0.0002

Data Index: 1624037 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8222. Min Act: -0.0002

Data Index: 1539946 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8177. Min Act: -0.0002

Data Index: 1475936 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.7912. Min Act: -0.0002

Data Index: 176148 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8097. Min Act: -0.0002

Data Index: 1392713 (Python Code)

Max Activating Token Index: 726

Text #16

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.7745. Min Act: -0.0002

Data Index: 1605275 (Python Code)

Max Activating Token Index: 961

Text #17

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.7819. Min Act: -0.0002

Data Index: 1613101 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.7399. Min Act: -0.0002

Data Index: 1478323 (Python Code)

Max Activating Token Index: 1021

Text #19

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.7599. Min Act: -0.0002

Data Index: 1425909 (Python Code)

Max Activating Token Index: 636