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

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

Neuron 2577 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0685. Min Act: -0.0000

Data Index: 903739 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0682. Min Act: -0.0000

Data Index: 749933 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0653. Min Act: -0.0001

Data Index: 6174 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0675. Min Act: -0.0001

Data Index: 153972 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0608. Min Act: -0.0001

Data Index: 963775 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0628. Min Act: -0.0001

Data Index: 188323 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1097785 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1093827 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0617. Min Act: -0.0001

Data Index: 850813 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1269703 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1213746 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1399572 (Python Code)

Max Activating Token Index: 420

Text #12

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1381747 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1427085 (Python Code)

Max Activating Token Index: 741

Text #14

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1550089 (Python Code)

Max Activating Token Index: 758

Text #15

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0557. Min Act: -0.0000

Data Index: 435144 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1192710 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1018192 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0488. Min Act: -0.0001

Data Index: 597971 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1073901 (C4 (Web Text))

Max Activating Token Index: 1011