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

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

Neuron 4666 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: 0.8834. Min Range: -0.8834

Max Act: 0.7459. Min Act: -0.0000

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8834. Min Act: -0.0000

Data Index: 509945 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1232178 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6873. Min Act: -0.0000

Data Index: 353993 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6773. Min Act: -0.0000

Data Index: 773725 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6581. Min Act: -0.0000

Data Index: 996401 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7124. Min Act: -0.0000

Data Index: 147451 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1071204 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1082832 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6562. Min Act: -0.0000

Data Index: 696351 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6658. Min Act: -0.0000

Data Index: 374089 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1252297 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1236149 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6615. Min Act: -0.0000

Data Index: 244641 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1311170 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1167932 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6102. Min Act: -0.0000

Data Index: 483866 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.5907. Min Act: -0.0000

Data Index: 805064 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6426. Min Act: -0.0000

Data Index: 189749 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.5838. Min Act: -0.0000

Data Index: 577371 (C4 (Web Text))

Max Activating Token Index: 978