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

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

Neuron 2082 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6132. Min Range: -2.6132

Max Act: 2.6132. Min Act: -0.0000

Data Index: 974282 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 2.6132. Min Range: -2.6132

Max Act: 2.4796. Min Act: -0.0000

Data Index: 138569 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 2.6132. Min Range: -2.6132

Max Act: 2.2824. Min Act: -0.0000

Data Index: 1092697 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.9518. Min Act: -0.0000

Data Index: 349600 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 2.6132. Min Range: -2.6132

Max Act: 2.0349. Min Act: -0.0000

Data Index: 886255 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 2.6132. Min Range: -2.6132

Max Act: 2.2283. Min Act: -0.0000

Data Index: 1343150 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.8627. Min Act: -0.0000

Data Index: 1088224 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.8732. Min Act: -0.0000

Data Index: 32454 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.8619. Min Act: 0.0000

Data Index: 773476 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.9125. Min Act: -0.0000

Data Index: 1326379 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.8147. Min Act: -0.0000

Data Index: 669487 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.8168. Min Act: -0.0000

Data Index: 184180 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.8110. Min Act: -0.0000

Data Index: 131373 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.7848. Min Act: -0.0000

Data Index: 772993 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.7733. Min Act: -0.0000

Data Index: 607903 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.7721. Min Act: -0.0000

Data Index: 251816 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.7356. Min Act: -0.0000

Data Index: 105733 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.7802. Min Act: -0.0000

Data Index: 586426 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.7807. Min Act: -0.0000

Data Index: 274846 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 2.6132. Min Range: -2.6132

Max Act: 1.6568. Min Act: -0.0000

Data Index: 132657 (C4 (Web Text))

Max Activating Token Index: 762