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

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

Neuron 236 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4038. Min Range: -4.4038

Max Act: 4.4038. Min Act: -0.0000

Data Index: 840282 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 4.4038. Min Range: -4.4038

Max Act: 3.9303. Min Act: -0.0000

Data Index: 66961 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 4.4038. Min Range: -4.4038

Max Act: 3.5302. Min Act: -0.0000

Data Index: 1267742 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 4.4038. Min Range: -4.4038

Max Act: 3.4019. Min Act: -0.0000

Data Index: 1114545 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 4.4038. Min Range: -4.4038

Max Act: 3.2858. Min Act: -0.0000

Data Index: 54137 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 4.4038. Min Range: -4.4038

Max Act: 3.1561. Min Act: -0.0000

Data Index: 1521109 (Python Code)

Max Activating Token Index: 348

Text #6

Max Range: 4.4038. Min Range: -4.4038

Max Act: 3.4367. Min Act: -0.0000

Data Index: 1063393 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.7126. Min Act: -0.0000

Data Index: 34490 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 4.4038. Min Range: -4.4038

Max Act: 3.4303. Min Act: -0.0000

Data Index: 813772 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.9867. Min Act: -0.0000

Data Index: 434795 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.5750. Min Act: -0.0000

Data Index: 1372319 (Python Code)

Max Activating Token Index: 863

Text #11

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.9362. Min Act: -0.0000

Data Index: 917332 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.7909. Min Act: -0.0000

Data Index: 332431 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.6363. Min Act: -0.0000

Data Index: 740975 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.7445. Min Act: -0.0000

Data Index: 1456671 (Python Code)

Max Activating Token Index: 970

Text #15

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.8917. Min Act: -0.0000

Data Index: 542208 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 4.4038. Min Range: -4.4038

Max Act: 3.1360. Min Act: -0.0000

Data Index: 881304 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.6245. Min Act: -0.0000

Data Index: 893818 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.7434. Min Act: -0.0000

Data Index: 571874 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 4.4038. Min Range: -4.4038

Max Act: 2.5997. Min Act: -0.0000

Data Index: 895136 (C4 (Web Text))

Max Activating Token Index: 687