Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3855 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0003

Data Index: 1205107 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0654. Min Act: -0.0003

Data Index: 301717 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0594. Min Act: -0.0003

Data Index: 88934 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0618. Min Act: -0.0003

Data Index: 202060 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0613. Min Act: -0.0003

Data Index: 394425 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0567. Min Act: -0.0003

Data Index: 138759 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0596. Min Act: -0.0003

Data Index: 253186 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0596. Min Act: -0.0004

Data Index: 1210858 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0548. Min Act: -0.0003

Data Index: 662912 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0618. Min Act: -0.0003

Data Index: 1008008 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0566. Min Act: -0.0003

Data Index: 666334 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0581. Min Act: -0.0003

Data Index: 569143 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0630. Min Act: -0.0003

Data Index: 998129 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1318968 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0575. Min Act: -0.0003

Data Index: 811129 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0594. Min Act: -0.0003

Data Index: 473458 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1080430 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0562. Min Act: -0.0003

Data Index: 429639 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0557. Min Act: -0.0003

Data Index: 146704 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0531. Min Act: -0.0003

Data Index: 198174 (C4 (Web Text))

Max Activating Token Index: 240