Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3337 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5044. Min Range: -2.5044

Max Act: 2.5044. Min Act: -0.0000

Data Index: 569005 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 2.5044. Min Range: -2.5044

Max Act: 2.3945. Min Act: -0.0000

Data Index: 1019119 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 2.5044. Min Range: -2.5044

Max Act: 2.2635. Min Act: -0.0000

Data Index: 767665 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 2.5044. Min Range: -2.5044

Max Act: 2.2298. Min Act: -0.0000

Data Index: 710697 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 2.5044. Min Range: -2.5044

Max Act: 2.1973. Min Act: -0.0000

Data Index: 851858 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 2.5044. Min Range: -2.5044

Max Act: 2.1637. Min Act: -0.0000

Data Index: 1275722 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.9137. Min Act: -0.0000

Data Index: 1537791 (Python Code)

Max Activating Token Index: 225

Text #7

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.8515. Min Act: -0.0000

Data Index: 3276 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.8611. Min Act: -0.0000

Data Index: 1605001 (Python Code)

Max Activating Token Index: 940

Text #9

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.8181. Min Act: -0.0000

Data Index: 353508 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 2.5044. Min Range: -2.5044

Max Act: 2.0164. Min Act: -0.0000

Data Index: 1063995 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 2.5044. Min Range: -2.5044

Max Act: 2.0009. Min Act: -0.0000

Data Index: 1025231 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.8742. Min Act: -0.0000

Data Index: 149263 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.7669. Min Act: -0.0000

Data Index: 169581 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.8689. Min Act: -0.0000

Data Index: 1039813 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.5704. Min Act: -0.0000

Data Index: 1013505 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.7675. Min Act: -0.0000

Data Index: 624373 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.8533. Min Act: -0.0000

Data Index: 909696 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.8282. Min Act: -0.0000

Data Index: 1089732 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.5044. Min Range: -2.5044

Max Act: 1.7308. Min Act: -0.0000

Data Index: 170777 (C4 (Web Text))

Max Activating Token Index: 341