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

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

Neuron 2900 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.9519. Min Act: -0.0000

Data Index: 171362 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.8938. Min Act: -0.0000

Data Index: 131278 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1250194 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1557594 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.7849. Min Act: -0.0000

Data Index: 288396 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1622221 (Python Code)

Max Activating Token Index: 941

Text #6

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1474939 (Python Code)

Max Activating Token Index: 1005

Text #7

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1457315 (Python Code)

Max Activating Token Index: 860

Text #8

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1421286 (Python Code)

Max Activating Token Index: 887

Text #9

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1578451 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1218297 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6626. Min Act: -0.0000

Data Index: 436024 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1419772 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.7065. Min Act: -0.0000

Data Index: 295402 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1558765 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1624201 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1509563 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6430. Min Act: -0.0000

Data Index: 235864 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1456331 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1415146 (Python Code)

Max Activating Token Index: 42