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

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

Neuron 765 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.9846. Min Act: -0.0000

Data Index: 1254149 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.2575. Min Act: -0.0000

Data Index: 159987 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.2260. Min Act: -0.0000

Data Index: 911748 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.1315. Min Act: -0.0000

Data Index: 1167504 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1138210 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.0594. Min Act: -0.0000

Data Index: 675919 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.0220. Min Act: -0.0000

Data Index: 931180 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.8915. Min Act: -0.0000

Data Index: 1316306 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1101245 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1303088 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 1.9846. Min Range: -1.9846

Max Act: 1.0142. Min Act: -0.0000

Data Index: 370422 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.9186. Min Act: -0.0000

Data Index: 10595 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.9282. Min Act: -0.0000

Data Index: 550470 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.9054. Min Act: -0.0000

Data Index: 594911 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.9621. Min Act: -0.0000

Data Index: 324440 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.8618. Min Act: -0.0000

Data Index: 309660 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1330228 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1087011 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.8549. Min Act: -0.0000

Data Index: 440682 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 1.9846. Min Range: -1.9846

Max Act: 0.7689. Min Act: -0.0000

Data Index: 556558 (C4 (Web Text))

Max Activating Token Index: 335