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

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

Neuron 3096 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4079. Min Range: -2.4079

Max Act: 2.4079. Min Act: -0.0000

Data Index: 1118206 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 2.4079. Min Range: -2.4079

Max Act: 2.0988. Min Act: -0.0000

Data Index: 1600712 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 2.4079. Min Range: -2.4079

Max Act: 2.3120. Min Act: -0.0000

Data Index: 383179 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 2.4079. Min Range: -2.4079

Max Act: 2.0382. Min Act: -0.0000

Data Index: 417793 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 2.4079. Min Range: -2.4079

Max Act: 2.0245. Min Act: -0.0000

Data Index: 640613 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 2.4079. Min Range: -2.4079

Max Act: 2.0740. Min Act: -0.0000

Data Index: 423388 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.9814. Min Act: -0.0000

Data Index: 1543902 (Python Code)

Max Activating Token Index: 280

Text #7

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.9775. Min Act: -0.0000

Data Index: 1472553 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 2.4079. Min Range: -2.4079

Max Act: 2.0321. Min Act: -0.0000

Data Index: 929894 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 2.4079. Min Range: -2.4079

Max Act: 2.0124. Min Act: -0.0000

Data Index: 1307085 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.8417. Min Act: -0.0000

Data Index: 858797 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.9114. Min Act: -0.0000

Data Index: 1047060 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.9247. Min Act: -0.0000

Data Index: 1655743 (Python Code)

Max Activating Token Index: 502

Text #13

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.8441. Min Act: -0.0000

Data Index: 429298 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.8827. Min Act: -0.0000

Data Index: 542345 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.8415. Min Act: -0.0000

Data Index: 1639014 (Python Code)

Max Activating Token Index: 161

Text #16

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.7783. Min Act: -0.0000

Data Index: 1366800 (Python Code)

Max Activating Token Index: 598

Text #17

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.8081. Min Act: -0.0000

Data Index: 1567553 (Python Code)

Max Activating Token Index: 652

Text #18

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.6875. Min Act: -0.0000

Data Index: 1533436 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 2.4079. Min Range: -2.4079

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1562959 (Python Code)

Max Activating Token Index: 486