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

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

Neuron 4966 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: 0.2597. Min Range: -0.2597

Max Act: 0.2597. Min Act: -0.0000

Data Index: 866309 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2500. Min Act: -0.0000

Data Index: 749945 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2210. Min Act: -0.0000

Data Index: 938555 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1950. Min Act: -0.0000

Data Index: 615453 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1953. Min Act: -0.0000

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1895. Min Act: -0.0000

Data Index: 958838 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1929. Min Act: -0.0000

Data Index: 570645 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1037755 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1745. Min Act: -0.0000

Data Index: 937500 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1354924 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1702. Min Act: -0.0000

Data Index: 387068 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1308044 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1794. Min Act: -0.0000

Data Index: 752917 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1732. Min Act: -0.0000

Data Index: 632380 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1607. Min Act: -0.0000

Data Index: 880850 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1313154 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1599. Min Act: -0.0000

Data Index: 889623 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1715. Min Act: -0.0000

Data Index: 20798 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1536. Min Act: -0.0000

Data Index: 827036 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1585. Min Act: -0.0000

Data Index: 645784 (C4 (Web Text))

Max Activating Token Index: 623