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

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

Neuron 3269 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.4421. Min Act: -0.0001

Data Index: 646149 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.4531. Min Act: -0.0001

Data Index: 194541 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.4024. Min Act: -0.0001

Data Index: 1295391 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3911. Min Act: -0.0001

Data Index: 1209957 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3876. Min Act: -0.0001

Data Index: 1150233 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3639. Min Act: -0.0001

Data Index: 349196 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3944. Min Act: -0.0001

Data Index: 257011 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3794. Min Act: -0.0001

Data Index: 843576 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3251. Min Act: -0.0001

Data Index: 896419 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3104. Min Act: -0.0001

Data Index: 1114826 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.2787. Min Act: -0.0001

Data Index: 1595645 (Python Code)

Max Activating Token Index: 606

Text #11

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.2522. Min Act: -0.0001

Data Index: 1601437 (Python Code)

Max Activating Token Index: 900

Text #12

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1424542 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.2394. Min Act: -0.0001

Data Index: 1572042 (Python Code)

Max Activating Token Index: 962

Text #14

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1447363 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.2436. Min Act: -0.0001

Data Index: 1536522 (Python Code)

Max Activating Token Index: 449

Text #16

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1567026 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.2209. Min Act: -0.0001

Data Index: 1613635 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1482829 (Python Code)

Max Activating Token Index: 911

Text #19

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1419433 (Python Code)

Max Activating Token Index: 828