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

Dataset: The Pile

Neuron 2016 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: 0.7102. Min Range: -0.7102

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1292605 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1841730 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.7051. Min Act: -0.0000

Data Index: 31028 (The Pile)

Max Activating Token Index: 916

Text #3

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1002156 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1935447 (The Pile)

Max Activating Token Index: 242

Text #5

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1564728 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1736936 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1437426 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1075834 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6071. Min Act: -0.0000

Data Index: 613447 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5876. Min Act: -0.0000

Data Index: 591797 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1172654 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6799. Min Act: -0.0000

Data Index: 924642 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1512546 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5217. Min Act: -0.0000

Data Index: 116092 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5455. Min Act: -0.0000

Data Index: 976866 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1562862 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5920. Min Act: -0.0000

Data Index: 689024 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5875. Min Act: -0.0000

Data Index: 994081 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5827. Min Act: -0.0000

Data Index: 698702 (The Pile)

Max Activating Token Index: 245