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

Dataset: The Pile

Neuron 3780 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: 0.2234. Min Range: -0.2234

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1646477 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.2234. Min Act: -0.0000

Data Index: 349336 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1979. Min Act: -0.0000

Data Index: 504290 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1094651 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1048084 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1578. Min Act: -0.0000

Data Index: 984223 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1848311 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1740. Min Act: -0.0000

Data Index: 884002 (The Pile)

Max Activating Token Index: 39

Text #8

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1449. Min Act: -0.0000

Data Index: 73057 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1428. Min Act: -0.0000

Data Index: 511920 (The Pile)

Max Activating Token Index: 197

Text #10

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1574. Min Act: -0.0000

Data Index: 545849 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1429. Min Act: -0.0000

Data Index: 489914 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1497302 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1502943 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1588189 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1497878 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1282. Min Act: -0.0000

Data Index: 812800 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1094673 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1408. Min Act: -0.0000

Data Index: 599222 (The Pile)

Max Activating Token Index: 691

Text #19

Max Range: 0.2234. Min Range: -0.2234

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1228646 (The Pile)

Max Activating Token Index: 821