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

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

Neuron 5756 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: 2.7728. Min Range: -2.7728

Max Act: 2.7728. Min Act: -0.0000

Data Index: 250383 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 2.7728. Min Range: -2.7728

Max Act: 2.3859. Min Act: -0.0000

Data Index: 309874 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 2.7728. Min Range: -2.7728

Max Act: 2.2451. Min Act: -0.0000

Data Index: 941734 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 2.7728. Min Range: -2.7728

Max Act: 2.2078. Min Act: -0.0000

Data Index: 700917 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 2.7728. Min Range: -2.7728

Max Act: 2.2058. Min Act: -0.0000

Data Index: 57661 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.9520. Min Act: -0.0000

Data Index: 336670 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.9697. Min Act: -0.0000

Data Index: 577198 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.7883. Min Act: -0.0000

Data Index: 289431 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.6056. Min Act: -0.0000

Data Index: 955769 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.6649. Min Act: -0.0000

Data Index: 148143 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.6370. Min Act: -0.0000

Data Index: 1185901 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.4679. Min Act: -0.0000

Data Index: 121512 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.5524. Min Act: -0.0000

Data Index: 1326410 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.3996. Min Act: -0.0000

Data Index: 1111916 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.2675. Min Act: -0.0000

Data Index: 48651 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.3213. Min Act: -0.0000

Data Index: 587246 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.3120. Min Act: -0.0000

Data Index: 739718 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.2961. Min Act: -0.0000

Data Index: 134739 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1059270 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 2.7728. Min Range: -2.7728

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1039236 (C4 (Web Text))

Max Activating Token Index: 349