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

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

Neuron 2645 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: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1383564 (Python Code)

Max Activating Token Index: 313

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1625651 (Python Code)

Max Activating Token Index: 496

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1546280 (Python Code)

Max Activating Token Index: 434

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1410863 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1470323 (Python Code)

Max Activating Token Index: 665

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1553399 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1493994 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1641933 (Python Code)

Max Activating Token Index: 828

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1434589 (Python Code)

Max Activating Token Index: 986

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1400306 (Python Code)

Max Activating Token Index: 585

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1649938 (Python Code)

Max Activating Token Index: 964

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1607247 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1435974 (Python Code)

Max Activating Token Index: 777

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1517117 (Python Code)

Max Activating Token Index: 641

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1364829 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1607311 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1625346 (Python Code)

Max Activating Token Index: 809

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1461565 (Python Code)

Max Activating Token Index: 844

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1435355 (Python Code)

Max Activating Token Index: 796

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1389940 (Python Code)

Max Activating Token Index: 657