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

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

Neuron 3155 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.4909. Min Range: -4.4909

Max Act: 4.4909. Min Act: -0.0000

Data Index: 1623245 (Python Code)

Max Activating Token Index: 198

Text #1

Max Range: 4.4909. Min Range: -4.4909

Max Act: 4.0786. Min Act: -0.0000

Data Index: 1629763 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 4.4909. Min Range: -4.4909

Max Act: 3.9805. Min Act: -0.0000

Data Index: 1556493 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 4.4909. Min Range: -4.4909

Max Act: 3.6103. Min Act: -0.0000

Data Index: 1483246 (Python Code)

Max Activating Token Index: 920

Text #4

Max Range: 4.4909. Min Range: -4.4909

Max Act: 3.5560. Min Act: -0.0000

Data Index: 1421041 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 4.4909. Min Range: -4.4909

Max Act: 3.1749. Min Act: -0.0000

Data Index: 1199879 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 4.4909. Min Range: -4.4909

Max Act: 3.4236. Min Act: -0.0000

Data Index: 1501939 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 4.4909. Min Range: -4.4909

Max Act: 3.4194. Min Act: -0.0000

Data Index: 1033973 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 4.4909. Min Range: -4.4909

Max Act: 2.9169. Min Act: -0.0000

Data Index: 1532133 (Python Code)

Max Activating Token Index: 635

Text #9

Max Range: 4.4909. Min Range: -4.4909

Max Act: 3.1972. Min Act: -0.0000

Data Index: 1510733 (Python Code)

Max Activating Token Index: 448

Text #10

Max Range: 4.4909. Min Range: -4.4909

Max Act: 3.3131. Min Act: -0.0000

Data Index: 1220266 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 4.4909. Min Range: -4.4909

Max Act: 3.4063. Min Act: -0.0000

Data Index: 1590504 (Python Code)

Max Activating Token Index: 1017

Text #12

Max Range: 4.4909. Min Range: -4.4909

Max Act: 2.9593. Min Act: -0.0000

Data Index: 349187 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 4.4909. Min Range: -4.4909

Max Act: 2.6971. Min Act: -0.0000

Data Index: 1566146 (Python Code)

Max Activating Token Index: 693

Text #14

Max Range: 4.4909. Min Range: -4.4909

Max Act: 2.8529. Min Act: -0.0000

Data Index: 1551891 (Python Code)

Max Activating Token Index: 184

Text #15

Max Range: 4.4909. Min Range: -4.4909

Max Act: 2.9270. Min Act: -0.0000

Data Index: 652674 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 4.4909. Min Range: -4.4909

Max Act: 2.8917. Min Act: -0.0000

Data Index: 500203 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 4.4909. Min Range: -4.4909

Max Act: 2.8420. Min Act: -0.0000

Data Index: 1362947 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 4.4909. Min Range: -4.4909

Max Act: 2.8292. Min Act: -0.0000

Data Index: 72477 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 4.4909. Min Range: -4.4909

Max Act: 2.6486. Min Act: -0.0000

Data Index: 472485 (C4 (Web Text))

Max Activating Token Index: 757