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

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

Neuron 883 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: 0.1886. Min Range: -0.1886

Max Act: 0.1886. Min Act: -0.0001

Data Index: 585656 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1756. Min Act: -0.0001

Data Index: 55904 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1565. Min Act: -0.0001

Data Index: 56072 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1038037 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1288967 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1492. Min Act: -0.0001

Data Index: 35714 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1477. Min Act: -0.0000

Data Index: 791856 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1477. Min Act: -0.0001

Data Index: 766496 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1455. Min Act: -0.0000

Data Index: 365857 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1430. Min Act: -0.0000

Data Index: 983658 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1019614 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1398. Min Act: -0.0001

Data Index: 20769 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1452. Min Act: -0.0000

Data Index: 286016 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1351. Min Act: -0.0001

Data Index: 351983 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1333326 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1320. Min Act: -0.0000

Data Index: 399946 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1246. Min Act: -0.0000

Data Index: 591806 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1267. Min Act: -0.0000

Data Index: 470981 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1154643 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1320. Min Act: -0.0000

Data Index: 274493 (C4 (Web Text))

Max Activating Token Index: 79