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

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

Neuron 547 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0947. Min Act: -0.0002

Data Index: 934445 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0863. Min Act: -0.0001

Data Index: 28484 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0780. Min Act: -0.0001

Data Index: 451877 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0809. Min Act: -0.0002

Data Index: 925808 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0812. Min Act: -0.0001

Data Index: 452296 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0667. Min Act: -0.0002

Data Index: 704467 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0651. Min Act: -0.0001

Data Index: 509727 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0677. Min Act: -0.0002

Data Index: 164569 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0670. Min Act: -0.0001

Data Index: 202967 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1075231 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1163349 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0597. Min Act: -0.0001

Data Index: 4720 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0643. Min Act: -0.0002

Data Index: 882212 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0653. Min Act: -0.0002

Data Index: 608416 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1238504 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1273113 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0602. Min Act: -0.0001

Data Index: 153156 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0569. Min Act: -0.0001

Data Index: 303279 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1005760 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0552. Min Act: -0.0002

Data Index: 582870 (C4 (Web Text))

Max Activating Token Index: 405