Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2645 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0112. Min Act: -0.0004

Data Index: 335082 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0115. Min Act: -0.0004

Data Index: 8817 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0109. Min Act: -0.0004

Data Index: 656573 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0113. Min Act: -0.0004

Data Index: 723855 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0096. Min Act: -0.0004

Data Index: 410067 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0104. Min Act: -0.0004

Data Index: 1174936 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0104. Min Act: -0.0004

Data Index: 556850 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0103. Min Act: -0.0004

Data Index: 266858 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0096. Min Act: -0.0004

Data Index: 622536 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0099. Min Act: -0.0004

Data Index: 878084 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0100. Min Act: -0.0004

Data Index: 600082 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0104. Min Act: -0.0004

Data Index: 1209068 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0094. Min Act: -0.0004

Data Index: 648058 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0088. Min Act: -0.0004

Data Index: 883035 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0098. Min Act: -0.0004

Data Index: 119503 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0102. Min Act: -0.0004

Data Index: 1262168 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0085. Min Act: -0.0004

Data Index: 885107 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0095. Min Act: -0.0004

Data Index: 319481 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0083. Min Act: -0.0004

Data Index: 1032564 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0103. Min Act: -0.0004

Data Index: 736659 (C4 (Web Text))

Max Activating Token Index: 239