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

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

Neuron 5239 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1391598 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9821. Min Act: -0.0000

Data Index: 1656613 (Python Code)

Max Activating Token Index: 57

Text #2

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.9216. Min Act: -0.0000

Data Index: 321293 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1481528 (Python Code)

Max Activating Token Index: 190

Text #4

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7859. Min Act: -0.0000

Data Index: 283284 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8069. Min Act: -0.0000

Data Index: 899314 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1593481 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1396215 (Python Code)

Max Activating Token Index: 267

Text #8

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1464160 (Python Code)

Max Activating Token Index: 1012

Text #9

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7522. Min Act: -0.0000

Data Index: 464391 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7465. Min Act: -0.0000

Data Index: 921531 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1602822 (Python Code)

Max Activating Token Index: 622

Text #12

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1612071 (Python Code)

Max Activating Token Index: 190

Text #13

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7467. Min Act: -0.0000

Data Index: 765499 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1596462 (Python Code)

Max Activating Token Index: 708

Text #15

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1641682 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.6853. Min Act: -0.0000

Data Index: 546187 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1560345 (Python Code)

Max Activating Token Index: 831

Text #18

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1611512 (Python Code)

Max Activating Token Index: 860

Text #19

Max Range: 0.9821. Min Range: -0.9821

Max Act: 0.7185. Min Act: -0.0000

Data Index: 419347 (C4 (Web Text))

Max Activating Token Index: 929