Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2528 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0713. Min Act: -0.0001

Data Index: 569642 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0596. Min Act: -0.0001

Data Index: 209916 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0619. Min Act: -0.0001

Data Index: 496778 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0614. Min Act: -0.0001

Data Index: 214494 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0476. Min Act: -0.0001

Data Index: 892743 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0512. Min Act: -0.0001

Data Index: 970036 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0504. Min Act: -0.0001

Data Index: 691902 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0503. Min Act: -0.0001

Data Index: 176922 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0431. Min Act: -0.0001

Data Index: 426378 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0488. Min Act: -0.0001

Data Index: 266827 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0490. Min Act: -0.0001

Data Index: 543416 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0418. Min Act: -0.0001

Data Index: 461585 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1514794 (Python Code)

Max Activating Token Index: 759

Text #13

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1025758 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0433. Min Act: -0.0001

Data Index: 121804 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0446. Min Act: -0.0001

Data Index: 527213 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1549704 (Python Code)

Max Activating Token Index: 950

Text #17

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1279507 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0445. Min Act: -0.0001

Data Index: 964030 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1109444 (C4 (Web Text))

Max Activating Token Index: 771