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

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

Neuron 1373 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0767. Min Act: -0.0002

Data Index: 541258 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0706. Min Act: -0.0002

Data Index: 210687 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0673. Min Act: -0.0002

Data Index: 556936 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1295381 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0620. Min Act: -0.0002

Data Index: 762904 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1086918 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0595. Min Act: -0.0002

Data Index: 209633 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1163576 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1294881 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0595. Min Act: -0.0002

Data Index: 605100 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1098736 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0571. Min Act: -0.0002

Data Index: 243419 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0623. Min Act: -0.0002

Data Index: 506891 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0576. Min Act: -0.0002

Data Index: 308964 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0570. Min Act: -0.0002

Data Index: 518257 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0565. Min Act: -0.0002

Data Index: 898067 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0541. Min Act: -0.0002

Data Index: 552127 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0556. Min Act: -0.0002

Data Index: 107554 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1319947 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0597. Min Act: -0.0002

Data Index: 264587 (C4 (Web Text))

Max Activating Token Index: 307