Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 596 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1791. Min Act: -0.0001

Data Index: 254481 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1661. Min Act: -0.0001

Data Index: 182485 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1022530 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1660. Min Act: -0.0001

Data Index: 206610 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1521. Min Act: -0.0001

Data Index: 641647 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1625. Min Act: -0.0001

Data Index: 619256 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1650. Min Act: -0.0000

Data Index: 950923 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1540. Min Act: -0.0000

Data Index: 65556 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1438. Min Act: -0.0001

Data Index: 686851 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1492. Min Act: -0.0000

Data Index: 328668 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1548. Min Act: -0.0001

Data Index: 588413 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1486. Min Act: 0.0000

Data Index: 928488 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1355. Min Act: -0.0000

Data Index: 345064 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1346981 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1504. Min Act: -0.0000

Data Index: 842317 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1466. Min Act: -0.0000

Data Index: 550204 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1423. Min Act: -0.0001

Data Index: 349199 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1418. Min Act: -0.0001

Data Index: 312774 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1370. Min Act: -0.0001

Data Index: 888580 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1473. Min Act: -0.0000

Data Index: 817009 (C4 (Web Text))

Max Activating Token Index: 212