Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1490 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0603. Min Act: -0.0005

Data Index: 1157979 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0588. Min Act: -0.0005

Data Index: 318777 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0539. Min Act: -0.0005

Data Index: 1245593 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0587. Min Act: -0.0005

Data Index: 1026480 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0521. Min Act: -0.0005

Data Index: 196272 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0557. Min Act: -0.0005

Data Index: 578658 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0537. Min Act: -0.0005

Data Index: 694245 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0530. Min Act: -0.0005

Data Index: 1335787 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0525. Min Act: -0.0005

Data Index: 853790 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0527. Min Act: -0.0005

Data Index: 370186 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0512. Min Act: -0.0005

Data Index: 657407 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0489. Min Act: -0.0005

Data Index: 114949 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0546. Min Act: -0.0005

Data Index: 929710 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0500. Min Act: -0.0005

Data Index: 436302 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0498. Min Act: -0.0005

Data Index: 1219286 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0465. Min Act: -0.0005

Data Index: 440961 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0485. Min Act: -0.0005

Data Index: 1033640 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0513. Min Act: -0.0005

Data Index: 745857 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0494. Min Act: -0.0005

Data Index: 1099532 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0503. Min Act: -0.0005

Data Index: 225434 (C4 (Web Text))

Max Activating Token Index: 898