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

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

Neuron 1741 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: 0.0937. Min Range: -0.0937

Max Act: 0.0890. Min Act: -0.0002

Data Index: 166204 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0937. Min Act: -0.0002

Data Index: 587687 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0773. Min Act: -0.0002

Data Index: 741301 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0708. Min Act: -0.0002

Data Index: 180044 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1137180 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1306418 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0709. Min Act: -0.0001

Data Index: 44911 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0745. Min Act: -0.0002

Data Index: 904647 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0545. Min Act: -0.0002

Data Index: 69510 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0632. Min Act: -0.0002

Data Index: 639630 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0673. Min Act: -0.0002

Data Index: 80785 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1198611 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0631. Min Act: -0.0001

Data Index: 48018 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0652. Min Act: -0.0002

Data Index: 477102 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1227223 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1196521 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0619. Min Act: -0.0002

Data Index: 398723 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1019914 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1195140 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1130658 (C4 (Web Text))

Max Activating Token Index: 151