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

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

Neuron 768 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.3613. Min Act: -0.0000

Data Index: 618152 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.7750. Min Act: -0.0001

Data Index: 1473926 (Python Code)

Max Activating Token Index: 279

Text #2

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.6592. Min Act: -0.0001

Data Index: 1420421 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.6004. Min Act: -0.0000

Data Index: 1417052 (Python Code)

Max Activating Token Index: 889

Text #4

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.5032. Min Act: -0.0001

Data Index: 1444006 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.4904. Min Act: 0.0000

Data Index: 1400310 (Python Code)

Max Activating Token Index: 787

Text #6

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.3613. Min Act: -0.0000

Data Index: 1542921 (Python Code)

Max Activating Token Index: 762

Text #7

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.5692. Min Act: -0.0000

Data Index: 1526027 (Python Code)

Max Activating Token Index: 507

Text #8

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.4362. Min Act: -0.0000

Data Index: 1387987 (Python Code)

Max Activating Token Index: 149

Text #9

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.4076. Min Act: 0.0001

Data Index: 1382560 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.3187. Min Act: -0.0000

Data Index: 468844 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.3435. Min Act: 0.0001

Data Index: 1467821 (Python Code)

Max Activating Token Index: 761

Text #12

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.4150. Min Act: -0.0000

Data Index: 1573542 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.3784. Min Act: -0.0000

Data Index: 1059988 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.3358. Min Act: -0.0000

Data Index: 376926 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.3385. Min Act: -0.0001

Data Index: 1608284 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.3989. Min Act: -0.0001

Data Index: 1423679 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.3120. Min Act: 0.0001

Data Index: 1478433 (Python Code)

Max Activating Token Index: 685

Text #18

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.3731. Min Act: 0.0000

Data Index: 1465120 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 2.3613. Min Range: -2.3613

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1415076 (Python Code)

Max Activating Token Index: 745