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

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

Neuron 345 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0597. Min Act: -0.0006

Data Index: 52900 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0633. Min Act: -0.0006

Data Index: 59860 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0648. Min Act: -0.0006

Data Index: 1336897 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0621. Min Act: -0.0006

Data Index: 79964 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0601. Min Act: -0.0006

Data Index: 243181 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0580. Min Act: -0.0006

Data Index: 843852 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0601. Min Act: -0.0006

Data Index: 682303 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0593. Min Act: -0.0006

Data Index: 568619 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0612. Min Act: -0.0006

Data Index: 926052 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0565. Min Act: -0.0006

Data Index: 108891 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0587. Min Act: -0.0006

Data Index: 836830 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0560. Min Act: -0.0006

Data Index: 889080 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0569. Min Act: -0.0006

Data Index: 257628 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0564. Min Act: -0.0006

Data Index: 549768 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0582. Min Act: -0.0006

Data Index: 431928 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0582. Min Act: -0.0006

Data Index: 166194 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0574. Min Act: -0.0006

Data Index: 838479 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0567. Min Act: -0.0006

Data Index: 594029 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0569. Min Act: -0.0006

Data Index: 839718 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0593. Min Act: -0.0006

Data Index: 1080311 (C4 (Web Text))

Max Activating Token Index: 339