Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 365 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0817. Min Act: -0.0003

Data Index: 953829 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0566. Min Act: -0.0003

Data Index: 1192228 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1118047 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0549. Min Act: -0.0004

Data Index: 89879 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0569. Min Act: -0.0003

Data Index: 944648 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0590. Min Act: -0.0003

Data Index: 412347 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0603. Min Act: -0.0003

Data Index: 175375 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0530. Min Act: -0.0003

Data Index: 292592 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0554. Min Act: -0.0003

Data Index: 526084 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0525. Min Act: -0.0003

Data Index: 31895 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0502. Min Act: -0.0004

Data Index: 402834 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0529. Min Act: -0.0003

Data Index: 225152 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0519. Min Act: -0.0003

Data Index: 835081 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1060361 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0505. Min Act: -0.0003

Data Index: 673076 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0491. Min Act: -0.0003

Data Index: 223625 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0478. Min Act: -0.0002

Data Index: 725333 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0493. Min Act: -0.0003

Data Index: 902728 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0506. Min Act: -0.0003

Data Index: 281667 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0519. Min Act: -0.0003

Data Index: 893423 (C4 (Web Text))

Max Activating Token Index: 92