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

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

Neuron 505 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0614. Min Act: -0.0006

Data Index: 1324905 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0590. Min Act: -0.0006

Data Index: 146747 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0607. Min Act: -0.0006

Data Index: 1249855 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0576. Min Act: -0.0006

Data Index: 797105 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0561. Min Act: -0.0006

Data Index: 877133 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0537. Min Act: -0.0006

Data Index: 1228841 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0517. Min Act: -0.0006

Data Index: 736458 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0512. Min Act: -0.0006

Data Index: 31685 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0506. Min Act: -0.0006

Data Index: 426735 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0516. Min Act: -0.0006

Data Index: 543547 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0515. Min Act: -0.0006

Data Index: 949613 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0482. Min Act: -0.0006

Data Index: 470700 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0473. Min Act: -0.0006

Data Index: 1098188 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0448. Min Act: -0.0006

Data Index: 201185 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0463. Min Act: -0.0006

Data Index: 988783 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0452. Min Act: -0.0006

Data Index: 1133236 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0449. Min Act: -0.0006

Data Index: 1040400 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0448. Min Act: -0.0006

Data Index: 1061013 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0449. Min Act: -0.0006

Data Index: 643964 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0443. Min Act: -0.0006

Data Index: 944576 (C4 (Web Text))

Max Activating Token Index: 524