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

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

Neuron 1549 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: 0.0780. Min Range: -0.0780

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1130160 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0780. Min Act: -0.0002

Data Index: 863522 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0711. Min Act: -0.0002

Data Index: 52414 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0708. Min Act: -0.0002

Data Index: 531454 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0687. Min Act: -0.0002

Data Index: 391004 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1084288 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0658. Min Act: -0.0002

Data Index: 767516 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1188368 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0626. Min Act: -0.0002

Data Index: 449084 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0647. Min Act: -0.0002

Data Index: 711428 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0626. Min Act: -0.0002

Data Index: 172355 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1129779 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0649. Min Act: -0.0002

Data Index: 611386 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0644. Min Act: -0.0002

Data Index: 87398 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0648. Min Act: -0.0002

Data Index: 564143 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0668. Min Act: -0.0002

Data Index: 716742 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1039691 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0617. Min Act: -0.0002

Data Index: 719451 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0643. Min Act: -0.0002

Data Index: 493858 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0657. Min Act: -0.0002

Data Index: 691720 (C4 (Web Text))

Max Activating Token Index: 553