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

Dataset: The Pile

Neuron 1354 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: 3.1292. Min Range: -3.1292

Max Act: 2.7962. Min Act: -0.0000

Data Index: 187924 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 3.1292. Min Range: -3.1292

Max Act: 3.1292. Min Act: -0.0000

Data Index: 568393 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.9535. Min Act: -0.0000

Data Index: 1059305 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.9060. Min Act: -0.0000

Data Index: 1107148 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7663. Min Act: -0.0000

Data Index: 505221 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.9014. Min Act: -0.0000

Data Index: 352523 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7625. Min Act: -0.0000

Data Index: 925492 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.8095. Min Act: -0.0000

Data Index: 1012485 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7330. Min Act: -0.0000

Data Index: 112902 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.9297. Min Act: -0.0000

Data Index: 1210077 (The Pile)

Max Activating Token Index: 1000

Text #10

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7907. Min Act: -0.0000

Data Index: 401286 (The Pile)

Max Activating Token Index: 351

Text #11

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.9177. Min Act: -0.0000

Data Index: 944117 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7623. Min Act: -0.0000

Data Index: 554870 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7805. Min Act: -0.0000

Data Index: 1329953 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7371. Min Act: -0.0000

Data Index: 176668 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7371. Min Act: -0.0000

Data Index: 1029870 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7357. Min Act: -0.0000

Data Index: 1829801 (The Pile)

Max Activating Token Index: 180

Text #17

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7305. Min Act: -0.0000

Data Index: 729386 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.7292. Min Act: -0.0000

Data Index: 1905605 (The Pile)

Max Activating Token Index: 492

Text #19

Max Range: 3.1292. Min Range: -3.1292

Max Act: 2.8714. Min Act: -0.0000

Data Index: 1392804 (The Pile)

Max Activating Token Index: 779