Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1689 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.5490. Min Act: -0.0000

Data Index: 768577 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.5398. Min Act: -0.0001

Data Index: 1359183 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1595396 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.1664. Min Act: -0.0000

Data Index: 426036 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.2940. Min Act: -0.0000

Data Index: 779596 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.0830. Min Act: -0.0001

Data Index: 1166287 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.0494. Min Act: -0.0000

Data Index: 884317 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9680. Min Act: -0.0000

Data Index: 395171 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9691. Min Act: -0.0000

Data Index: 19021 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.0983. Min Act: -0.0001

Data Index: 847235 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9351. Min Act: -0.0001

Data Index: 1220725 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9291. Min Act: -0.0000

Data Index: 922594 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9186. Min Act: -0.0000

Data Index: 349801 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9747. Min Act: -0.0000

Data Index: 95749 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1404819 (Python Code)

Max Activating Token Index: 920

Text #15

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9911. Min Act: -0.0001

Data Index: 482208 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.0355. Min Act: -0.0001

Data Index: 800789 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9127. Min Act: -0.0000

Data Index: 337885 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9561. Min Act: -0.0000

Data Index: 689713 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9768. Min Act: -0.0000

Data Index: 1273476 (C4 (Web Text))

Max Activating Token Index: 767