Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4746 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1125658 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0665. Min Act: -0.0003

Data Index: 613886 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1049578 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0626. Min Act: -0.0003

Data Index: 616204 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0638. Min Act: -0.0002

Data Index: 147541 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0609. Min Act: -0.0003

Data Index: 359345 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0575. Min Act: -0.0003

Data Index: 303847 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1119895 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1047667 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0530. Min Act: -0.0003

Data Index: 948360 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0509. Min Act: -0.0002

Data Index: 778808 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0478. Min Act: -0.0002

Data Index: 711781 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0475. Min Act: -0.0002

Data Index: 712915 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0539. Min Act: -0.0003

Data Index: 72195 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0467. Min Act: -0.0002

Data Index: 483156 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0463. Min Act: -0.0003

Data Index: 35697 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0446. Min Act: -0.0003

Data Index: 311255 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0458. Min Act: -0.0003

Data Index: 521162 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0459. Min Act: -0.0003

Data Index: 163122 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0452. Min Act: -0.0003

Data Index: 562374 (C4 (Web Text))

Max Activating Token Index: 310