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

Dataset: The Pile

Neuron 423 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2257. Min Act: -0.0000

Data Index: 634210 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1895154 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1724. Min Act: -0.0000

Data Index: 546811 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1766. Min Act: -0.0000

Data Index: 114825 (The Pile)

Max Activating Token Index: 415

Text #4

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1741. Min Act: -0.0000

Data Index: 105364 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1975585 (The Pile)

Max Activating Token Index: 690

Text #6

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1612. Min Act: -0.0000

Data Index: 157960 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1443186 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1226038 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1514485 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1466. Min Act: -0.0000

Data Index: 877076 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1116397 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1486207 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1568. Min Act: -0.0000

Data Index: 341682 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1209875 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1531. Min Act: -0.0000

Data Index: 54477 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1418. Min Act: -0.0000

Data Index: 114098 (The Pile)

Max Activating Token Index: 160

Text #17

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1036225 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1491. Min Act: -0.0000

Data Index: 264438 (The Pile)

Max Activating Token Index: 678

Text #19

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1398. Min Act: -0.0000

Data Index: 946613 (The Pile)

Max Activating Token Index: 611