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

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

Neuron 3552 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: 1.3950. Min Range: -1.3950

Max Act: 1.3950. Min Act: -0.0000

Data Index: 1108359 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.1294. Min Act: -0.0000

Data Index: 145348 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1243496 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.9379. Min Act: -0.0000

Data Index: 418564 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.9610. Min Act: -0.0000

Data Index: 250382 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0052. Min Act: -0.0000

Data Index: 763703 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.9085. Min Act: -0.0000

Data Index: 660953 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1301998 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.9243. Min Act: -0.0000

Data Index: 489777 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8591. Min Act: -0.0000

Data Index: 613845 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1213799 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1075134 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.9391. Min Act: -0.0000

Data Index: 587273 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8765. Min Act: -0.0000

Data Index: 693306 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8411. Min Act: -0.0000

Data Index: 525648 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8501. Min Act: -0.0000

Data Index: 842871 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8156. Min Act: -0.0000

Data Index: 700723 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8612. Min Act: -0.0000

Data Index: 589649 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1167068 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1346513 (C4 (Web Text))

Max Activating Token Index: 809