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

Dataset: The Pile

Neuron 3651 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.1109. Min Act: -0.0000

Data Index: 18016 (The Pile)

Max Activating Token Index: 546

Text #1

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.0330. Min Act: -0.0000

Data Index: 726527 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1949561 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1279315 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9053. Min Act: -0.0000

Data Index: 217795 (The Pile)

Max Activating Token Index: 868

Text #5

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9336. Min Act: -0.0000

Data Index: 867901 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1507407 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8917. Min Act: -0.0000

Data Index: 601052 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8951. Min Act: -0.0000

Data Index: 737869 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1410697 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8519. Min Act: -0.0000

Data Index: 1813351 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1826867 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1765517 (The Pile)

Max Activating Token Index: 525

Text #13

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8393. Min Act: -0.0000

Data Index: 29230 (The Pile)

Max Activating Token Index: 114

Text #14

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8359. Min Act: -0.0000

Data Index: 506616 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.7993. Min Act: -0.0000

Data Index: 850212 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8251. Min Act: -0.0000

Data Index: 793922 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1408254 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1902713 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1533357 (The Pile)

Max Activating Token Index: 975