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

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

Neuron 2306 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1845. Min Act: -0.0003

Data Index: 1209112 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.2046. Min Act: -0.0003

Data Index: 261934 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1918. Min Act: -0.0003

Data Index: 510521 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1782. Min Act: -0.0003

Data Index: 852927 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1499. Min Act: -0.0003

Data Index: 146015 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1540. Min Act: -0.0003

Data Index: 831939 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1712. Min Act: -0.0003

Data Index: 349333 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1625. Min Act: -0.0003

Data Index: 468321 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1371. Min Act: -0.0003

Data Index: 632211 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1412. Min Act: -0.0003

Data Index: 523503 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1699. Min Act: -0.0003

Data Index: 751351 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1521. Min Act: -0.0003

Data Index: 383798 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1583. Min Act: -0.0003

Data Index: 635904 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1475. Min Act: -0.0003

Data Index: 34750 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1509. Min Act: -0.0003

Data Index: 207437 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1434. Min Act: -0.0003

Data Index: 1166285 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1556. Min Act: -0.0003

Data Index: 46386 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1403. Min Act: -0.0003

Data Index: 51640 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1483. Min Act: -0.0003

Data Index: 263633 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1527. Min Act: -0.0003

Data Index: 103100 (C4 (Web Text))

Max Activating Token Index: 173