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

Dataset: The Pile

Neuron 969 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: 0.8953. Min Range: -0.8953

Max Act: 0.8129. Min Act: -0.0000

Data Index: 550108 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8537. Min Act: -0.0000

Data Index: 602854 (The Pile)

Max Activating Token Index: 35

Text #2

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8953. Min Act: 0.0000

Data Index: 1187970 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1957669 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8383. Min Act: 0.0001

Data Index: 531107 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1240668 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1377176 (The Pile)

Max Activating Token Index: 650

Text #7

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1036186 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7337. Min Act: 0.0000

Data Index: 156016 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1493848 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7858. Min Act: -0.0000

Data Index: 767024 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1097816 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7172. Min Act: -0.0000

Data Index: 909526 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7204. Min Act: 0.0000

Data Index: 725642 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1411387 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1971319 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1260687 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1353398 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6608. Min Act: 0.0000

Data Index: 1764382 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7702. Min Act: -0.0000

Data Index: 329740 (The Pile)

Max Activating Token Index: 976