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

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

Neuron 2820 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1491. Min Range: -1.1491

Max Act: 1.1491. Min Act: -0.0000

Data Index: 408268 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 1.1491. Min Range: -1.1491

Max Act: 1.0908. Min Act: -0.0000

Data Index: 720260 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8745. Min Act: -0.0000

Data Index: 650364 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.8452. Min Act: -0.0000

Data Index: 732036 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7675. Min Act: -0.0000

Data Index: 244188 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1264607 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7023. Min Act: -0.0000

Data Index: 975962 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1050044 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6877. Min Act: -0.0000

Data Index: 234240 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1310892 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7527. Min Act: -0.0000

Data Index: 628898 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7124. Min Act: -0.0000

Data Index: 470639 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7265. Min Act: -0.0000

Data Index: 765526 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1060532 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1088194 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1199629 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1295616 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.7014. Min Act: -0.0000

Data Index: 882076 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1013276 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 1.1491. Min Range: -1.1491

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1126815 (C4 (Web Text))

Max Activating Token Index: 895