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

Dataset: The Pile

Neuron 1536 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1403. Min Act: -0.0000

Data Index: 529711 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1308. Min Act: 0.0000

Data Index: 478407 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1253. Min Act: -0.0000

Data Index: 853776 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1298297 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1619819 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1085. Min Act: -0.0000

Data Index: 246614 (The Pile)

Max Activating Token Index: 857

Text #6

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1162325 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1928355 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1087363 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1184. Min Act: -0.0000

Data Index: 494909 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1014. Min Act: -0.0000

Data Index: 255921 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1462769 (The Pile)

Max Activating Token Index: 14

Text #12

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1595394 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1096. Min Act: -0.0000

Data Index: 667947 (The Pile)

Max Activating Token Index: 911

Text #14

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1588935 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1031. Min Act: -0.0000

Data Index: 120665 (The Pile)

Max Activating Token Index: 894

Text #16

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1149. Min Act: -0.0000

Data Index: 645195 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1445189 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1715276 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1348699 (The Pile)

Max Activating Token Index: 833