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

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

Neuron 4321 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.1184. Min Act: -0.0001

Data Index: 652368 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.7644. Min Act: -0.0001

Data Index: 1326880 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6455. Min Act: -0.0001

Data Index: 1175258 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6683. Min Act: -0.0001

Data Index: 788266 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6559. Min Act: -0.0001

Data Index: 755916 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6727. Min Act: -0.0001

Data Index: 824984 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6495. Min Act: -0.0001

Data Index: 641745 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6453. Min Act: -0.0001

Data Index: 1193524 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6687. Min Act: -0.0001

Data Index: 912384 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6392. Min Act: -0.0001

Data Index: 700228 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6417. Min Act: -0.0001

Data Index: 885903 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6535. Min Act: -0.0001

Data Index: 1069572 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6148. Min Act: -0.0001

Data Index: 429543 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6016. Min Act: -0.0001

Data Index: 766516 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.5923. Min Act: -0.0001

Data Index: 973468 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.5640. Min Act: -0.0001

Data Index: 383653 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6273. Min Act: -0.0001

Data Index: 618465 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.5915. Min Act: -0.0001

Data Index: 806957 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.5942. Min Act: -0.0001

Data Index: 1292429 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6160. Min Act: -0.0001

Data Index: 1296656 (C4 (Web Text))

Max Activating Token Index: 774