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

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

Neuron 136 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: 0.0621. Min Range: -0.0621

Max Act: 0.0612. Min Act: -0.0006

Data Index: 247474 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0006

Data Index: 1021439 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0617. Min Act: -0.0006

Data Index: 954798 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0594. Min Act: -0.0006

Data Index: 358986 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0604. Min Act: -0.0006

Data Index: 216152 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0600. Min Act: -0.0006

Data Index: 331146 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0587. Min Act: -0.0006

Data Index: 1124801 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0611. Min Act: -0.0006

Data Index: 728194 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0585. Min Act: -0.0006

Data Index: 512874 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0594. Min Act: -0.0006

Data Index: 423261 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0593. Min Act: -0.0006

Data Index: 624087 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0593. Min Act: -0.0006

Data Index: 510209 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0604. Min Act: -0.0006

Data Index: 760776 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0578. Min Act: -0.0006

Data Index: 149917 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0566. Min Act: -0.0006

Data Index: 431065 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0562. Min Act: -0.0006

Data Index: 569270 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0574. Min Act: -0.0006

Data Index: 1117608 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0584. Min Act: -0.0006

Data Index: 524178 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0584. Min Act: -0.0006

Data Index: 409904 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0573. Min Act: -0.0006

Data Index: 96840 (C4 (Web Text))

Max Activating Token Index: 807