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

Dataset: The Pile

Neuron 3630 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: 0.2346. Min Range: -0.2346

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1213488 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1679. Min Act: -0.0000

Data Index: 1132851 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1350302 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1252410 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1939389 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1633596 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1711371 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1117. Min Act: -0.0000

Data Index: 483252 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1565416 (The Pile)

Max Activating Token Index: 150

Text #9

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1588952 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1277783 (The Pile)

Max Activating Token Index: 868

Text #11

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1157. Min Act: -0.0000

Data Index: 969695 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1726957 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1180. Min Act: -0.0000

Data Index: 884277 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1882714 (The Pile)

Max Activating Token Index: 680

Text #15

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1856059 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1064. Min Act: -0.0000

Data Index: 856556 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.0990. Min Act: -0.0000

Data Index: 650124 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1076. Min Act: -0.0000

Data Index: 168238 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1622224 (The Pile)

Max Activating Token Index: 771