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

Dataset: The Pile

Neuron 802 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: 0.1788. Min Range: -0.1788

Max Act: 0.1788. Min Act: -0.0000

Data Index: 183719 (The Pile)

Max Activating Token Index: 507

Text #1

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1603. Min Act: -0.0000

Data Index: 117699 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1685535 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1705483 (The Pile)

Max Activating Token Index: 896

Text #4

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1304665 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1154232 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1251. Min Act: -0.0000

Data Index: 593945 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1302665 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1339. Min Act: -0.0000

Data Index: 785597 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1178. Min Act: -0.0000

Data Index: 724554 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1230. Min Act: -0.0000

Data Index: 986020 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1175. Min Act: -0.0000

Data Index: 674409 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1270. Min Act: -0.0000

Data Index: 523983 (The Pile)

Max Activating Token Index: 666

Text #13

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1124. Min Act: -0.0000

Data Index: 232541 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1714689 (The Pile)

Max Activating Token Index: 415

Text #15

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1143. Min Act: -0.0000

Data Index: 53882 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1908319 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1842547 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1172. Min Act: -0.0000

Data Index: 101988 (The Pile)

Max Activating Token Index: 263

Text #19

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1841919 (The Pile)

Max Activating Token Index: 271