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

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

Neuron 4702 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2447. Min Act: -0.0002

Data Index: 369486 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2121. Min Act: -0.0002

Data Index: 850194 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1930. Min Act: -0.0002

Data Index: 458009 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1994. Min Act: -0.0002

Data Index: 1155545 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1718. Min Act: -0.0002

Data Index: 452050 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1563. Min Act: -0.0003

Data Index: 279358 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1529. Min Act: -0.0002

Data Index: 493987 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1510. Min Act: -0.0002

Data Index: 222369 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1584. Min Act: -0.0003

Data Index: 1203712 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1524. Min Act: -0.0003

Data Index: 1606232 (Python Code)

Max Activating Token Index: 586

Text #10

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1566. Min Act: -0.0002

Data Index: 320544 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1386. Min Act: -0.0002

Data Index: 784746 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1374. Min Act: -0.0003

Data Index: 377987 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1456. Min Act: -0.0002

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1354. Min Act: -0.0003

Data Index: 20405 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1341. Min Act: -0.0003

Data Index: 207290 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1381. Min Act: -0.0003

Data Index: 466736 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1327. Min Act: -0.0003

Data Index: 1547873 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1360. Min Act: -0.0002

Data Index: 1177174 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1498101 (Python Code)

Max Activating Token Index: 304