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

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

Neuron 2813 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5882. Min Range: -2.5882

Max Act: 2.5882. Min Act: -0.0000

Data Index: 1563184 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 2.5882. Min Range: -2.5882

Max Act: 2.0745. Min Act: -0.0000

Data Index: 1094755 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 2.5882. Min Range: -2.5882

Max Act: 2.0118. Min Act: -0.0000

Data Index: 133267 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 2.5882. Min Range: -2.5882

Max Act: 2.0848. Min Act: -0.0000

Data Index: 1568486 (Python Code)

Max Activating Token Index: 169

Text #4

Max Range: 2.5882. Min Range: -2.5882

Max Act: 2.0899. Min Act: -0.0000

Data Index: 296376 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.9344. Min Act: -0.0000

Data Index: 1572502 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.8368. Min Act: -0.0000

Data Index: 1521083 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.9317. Min Act: -0.0000

Data Index: 1649375 (Python Code)

Max Activating Token Index: 691

Text #8

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.9194. Min Act: -0.0000

Data Index: 1361279 (Python Code)

Max Activating Token Index: 161

Text #9

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.7843. Min Act: -0.0000

Data Index: 1476172 (Python Code)

Max Activating Token Index: 884

Text #10

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.8926. Min Act: -0.0000

Data Index: 1418334 (Python Code)

Max Activating Token Index: 470

Text #11

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.7793. Min Act: -0.0000

Data Index: 1479600 (Python Code)

Max Activating Token Index: 110

Text #12

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.8458. Min Act: -0.0000

Data Index: 1527759 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.8237. Min Act: -0.0000

Data Index: 1276127 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.8039. Min Act: -0.0000

Data Index: 1543573 (Python Code)

Max Activating Token Index: 862

Text #15

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.7067. Min Act: -0.0000

Data Index: 1001299 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.7606. Min Act: -0.0000

Data Index: 1447048 (Python Code)

Max Activating Token Index: 339

Text #17

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.7750. Min Act: -0.0000

Data Index: 1385749 (Python Code)

Max Activating Token Index: 897

Text #18

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.7349. Min Act: -0.0000

Data Index: 1392191 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 2.5882. Min Range: -2.5882

Max Act: 1.7230. Min Act: -0.0000

Data Index: 1600240 (Python Code)

Max Activating Token Index: 154