Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5015 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6745. Min Act: -0.0001

Data Index: 224986 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.7180. Min Act: -0.0001

Data Index: 762942 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6061. Min Act: -0.0001

Data Index: 1244487 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6496. Min Act: -0.0001

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6054. Min Act: -0.0001

Data Index: 511518 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6617. Min Act: -0.0001

Data Index: 1242397 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6744. Min Act: -0.0001

Data Index: 855979 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6061. Min Act: -0.0001

Data Index: 1135450 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6308. Min Act: -0.0001

Data Index: 80468 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6095. Min Act: -0.0001

Data Index: 956383 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.5829. Min Act: -0.0001

Data Index: 48663 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6370. Min Act: -0.0001

Data Index: 1203491 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.5588. Min Act: -0.0001

Data Index: 20647 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6544. Min Act: -0.0001

Data Index: 232463 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6221. Min Act: -0.0001

Data Index: 120956 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.5714. Min Act: -0.0001

Data Index: 59099 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.5797. Min Act: -0.0001

Data Index: 214051 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.5784. Min Act: -0.0001

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.5958. Min Act: -0.0001

Data Index: 1337215 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.7180. Min Range: -0.7180

Max Act: 0.6373. Min Act: -0.0001

Data Index: 1312786 (C4 (Web Text))

Max Activating Token Index: 212