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

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

Neuron 4305 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.8660. Min Act: -0.0000

Data Index: 428520 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.5221. Min Act: -0.0000

Data Index: 59783 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.3811. Min Act: -0.0000

Data Index: 459225 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.1800. Min Act: -0.0000

Data Index: 1288233 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.1413. Min Act: -0.0000

Data Index: 1303536 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.2727. Min Act: -0.0000

Data Index: 131167 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.1243. Min Act: -0.0000

Data Index: 773503 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.9868. Min Act: -0.0000

Data Index: 1320547 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.9215. Min Act: -0.0000

Data Index: 1319745 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.8987. Min Act: -0.0000

Data Index: 955189 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.0104. Min Act: -0.0000

Data Index: 874055 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.7259. Min Act: -0.0000

Data Index: 1111106 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.9800. Min Act: -0.0000

Data Index: 377801 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.0682. Min Act: -0.0000

Data Index: 980543 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.7782. Min Act: -0.0000

Data Index: 225349 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.7696. Min Act: -0.0000

Data Index: 847903 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.8642. Min Act: -0.0000

Data Index: 949259 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.7069. Min Act: -0.0000

Data Index: 448545 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.6617. Min Act: -0.0000

Data Index: 367666 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 3.8660. Min Range: -3.8660

Max Act: 2.5268. Min Act: -0.0000

Data Index: 726481 (C4 (Web Text))

Max Activating Token Index: 699