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

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

Neuron 1603 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1773. Min Range: -3.1773

Max Act: 3.1773. Min Act: -0.0000

Data Index: 1452806 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 3.1773. Min Range: -3.1773

Max Act: 1.5320. Min Act: -0.0000

Data Index: 1490005 (Python Code)

Max Activating Token Index: 987

Text #2

Max Range: 3.1773. Min Range: -3.1773

Max Act: 1.2144. Min Act: -0.0000

Data Index: 204174 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.1773. Min Range: -3.1773

Max Act: 1.1868. Min Act: -0.0000

Data Index: 72203 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 3.1773. Min Range: -3.1773

Max Act: 1.0938. Min Act: -0.0000

Data Index: 934806 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 3.1773. Min Range: -3.1773

Max Act: 1.0001. Min Act: -0.0000

Data Index: 506120 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 3.1773. Min Range: -3.1773

Max Act: 1.0519. Min Act: -0.0000

Data Index: 234246 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.9561. Min Act: -0.0000

Data Index: 385728 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.9384. Min Act: -0.0000

Data Index: 846033 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 3.1773. Min Range: -3.1773

Max Act: 1.0116. Min Act: -0.0000

Data Index: 130426 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 3.1773. Min Range: -3.1773

Max Act: 1.0355. Min Act: -0.0000

Data Index: 358393 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.9614. Min Act: -0.0000

Data Index: 734602 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.9923. Min Act: -0.0000

Data Index: 526617 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.9522. Min Act: -0.0000

Data Index: 207564 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1260298 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.9949. Min Act: -0.0000

Data Index: 548689 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1228147 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1074149 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.9071. Min Act: -0.0000

Data Index: 129537 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 3.1773. Min Range: -3.1773

Max Act: 0.8453. Min Act: -0.0000

Data Index: 789756 (C4 (Web Text))

Max Activating Token Index: 1023