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

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

Neuron 380 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: 4.8066. Min Range: -4.8066

Max Act: 4.5049. Min Act: -0.0000

Data Index: 563685 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.8066. Min Act: -0.0000

Data Index: 1357533 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.3881. Min Act: -0.0000

Data Index: 950728 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.1901. Min Act: -0.0000

Data Index: 990307 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.3856. Min Act: -0.0000

Data Index: 269672 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.8893. Min Act: -0.0000

Data Index: 452695 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.8917. Min Act: -0.0000

Data Index: 1087366 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.9020. Min Act: -0.0000

Data Index: 45886 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.9070. Min Act: -0.0000

Data Index: 393977 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.8549. Min Act: -0.0000

Data Index: 625410 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.7891. Min Act: -0.0000

Data Index: 682647 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.9390. Min Act: -0.0000

Data Index: 234117 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.2405. Min Act: -0.0000

Data Index: 711789 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.9125. Min Act: -0.0000

Data Index: 166388 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.8400. Min Act: -0.0000

Data Index: 349002 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.9858. Min Act: -0.0000

Data Index: 699998 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.8076. Min Act: -0.0000

Data Index: 758356 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.6511. Min Act: -0.0000

Data Index: 1128895 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.6517. Min Act: -0.0000

Data Index: 61928 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 4.8066. Min Range: -4.8066

Max Act: 3.7908. Min Act: -0.0000

Data Index: 1241141 (C4 (Web Text))

Max Activating Token Index: 367