Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2847 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.6404. Min Act: -0.0004

Data Index: 1389896 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.6115. Min Act: -0.0004

Data Index: 1468376 (Python Code)

Max Activating Token Index: 264

Text #2

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5905. Min Act: -0.0004

Data Index: 1452854 (Python Code)

Max Activating Token Index: 383

Text #3

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5864. Min Act: -0.0004

Data Index: 1622875 (Python Code)

Max Activating Token Index: 474

Text #4

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4887. Min Act: -0.0004

Data Index: 1627775 (Python Code)

Max Activating Token Index: 863

Text #5

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.6061. Min Act: -0.0004

Data Index: 1625742 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5061. Min Act: -0.0004

Data Index: 1634814 (Python Code)

Max Activating Token Index: 865

Text #7

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5916. Min Act: -0.0004

Data Index: 1455097 (Python Code)

Max Activating Token Index: 680

Text #8

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4443. Min Act: -0.0004

Data Index: 1511964 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4281. Min Act: -0.0004

Data Index: 1605337 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5394. Min Act: -0.0004

Data Index: 1474634 (Python Code)

Max Activating Token Index: 574

Text #11

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5207. Min Act: -0.0004

Data Index: 1504439 (Python Code)

Max Activating Token Index: 504

Text #12

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5353. Min Act: -0.0004

Data Index: 1555436 (Python Code)

Max Activating Token Index: 521

Text #13

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4628. Min Act: -0.0004

Data Index: 1547400 (Python Code)

Max Activating Token Index: 256

Text #14

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5667. Min Act: -0.0004

Data Index: 1421368 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5125. Min Act: -0.0004

Data Index: 1496178 (Python Code)

Max Activating Token Index: 986

Text #16

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4773. Min Act: -0.0004

Data Index: 1588662 (Python Code)

Max Activating Token Index: 553

Text #17

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5398. Min Act: -0.0004

Data Index: 1599699 (Python Code)

Max Activating Token Index: 779

Text #18

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5227. Min Act: -0.0004

Data Index: 1411964 (Python Code)

Max Activating Token Index: 818

Text #19

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4839. Min Act: -0.0004

Data Index: 1581249 (Python Code)

Max Activating Token Index: 160