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

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

Neuron 1286 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1405880 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1563304 (Python Code)

Max Activating Token Index: 192

Text #2

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1073809 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1428207 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1430777 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0660. Min Act: -0.0002

Data Index: 887845 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0661. Min Act: -0.0002

Data Index: 759147 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1412833 (Python Code)

Max Activating Token Index: 766

Text #8

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0611. Min Act: -0.0002

Data Index: 361185 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0550. Min Act: -0.0002

Data Index: 46642 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1470297 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0519. Min Act: -0.0002

Data Index: 439177 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0544. Min Act: -0.0002

Data Index: 578552 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0568. Min Act: -0.0002

Data Index: 463750 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0593. Min Act: -0.0002

Data Index: 22897 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1511395 (Python Code)

Max Activating Token Index: 522

Text #16

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0609. Min Act: -0.0002

Data Index: 451327 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1386512 (Python Code)

Max Activating Token Index: 860

Text #18

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0554. Min Act: -0.0002

Data Index: 106636 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0532. Min Act: -0.0002

Data Index: 716215 (C4 (Web Text))

Max Activating Token Index: 800