Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3273 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.7091. Min Act: -0.0000

Data Index: 618520 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.6713. Min Act: -0.0000

Data Index: 796887 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.6913. Min Act: -0.0000

Data Index: 879504 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1213323 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.6059. Min Act: -0.0000

Data Index: 505895 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.5142. Min Act: -0.0000

Data Index: 194002 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.5105. Min Act: -0.0000

Data Index: 552647 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4638. Min Act: -0.0000

Data Index: 981839 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1285597 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4345. Min Act: -0.0000

Data Index: 206867 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4807. Min Act: -0.0000

Data Index: 238765 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4630. Min Act: -0.0000

Data Index: 504900 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1253893 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4356. Min Act: -0.0000

Data Index: 887491 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1005426 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4148. Min Act: -0.0000

Data Index: 515725 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4119. Min Act: -0.0000

Data Index: 989661 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4122. Min Act: -0.0000

Data Index: 960397 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4227. Min Act: -0.0000

Data Index: 473496 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.7091. Min Range: -0.7091

Max Act: 0.4301. Min Act: -0.0000

Data Index: 84980 (C4 (Web Text))

Max Activating Token Index: 1004