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

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

Neuron 1438 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: 0.7552. Min Range: -0.7552

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1245693 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1584297 (Python Code)

Max Activating Token Index: 294

Text #2

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1120687 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5568. Min Act: -0.0000

Data Index: 251119 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1557386 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5129. Min Act: -0.0000

Data Index: 757980 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1476012 (Python Code)

Max Activating Token Index: 881

Text #7

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1289954 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1554356 (Python Code)

Max Activating Token Index: 212

Text #9

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4505. Min Act: -0.0000

Data Index: 498 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4467. Min Act: -0.0000

Data Index: 218471 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4172. Min Act: -0.0000

Data Index: 285581 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4187. Min Act: -0.0000

Data Index: 748196 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4089. Min Act: -0.0000

Data Index: 606044 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1417398 (Python Code)

Max Activating Token Index: 635

Text #15

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1200384 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1412731 (Python Code)

Max Activating Token Index: 886

Text #17

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1443945 (Python Code)

Max Activating Token Index: 572

Text #18

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1636135 (Python Code)

Max Activating Token Index: 744

Text #19

Max Range: 0.7552. Min Range: -0.7552

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1561536 (Python Code)

Max Activating Token Index: 724