Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 6 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1379850 (Python Code)

Max Activating Token Index: 872

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0001

Data Index: 872631 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1494961 (Python Code)

Max Activating Token Index: 870

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0401. Min Act: -0.0001

Data Index: 490876 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1118380 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1208426 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0360. Min Act: -0.0001

Data Index: 696283 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1478300 (Python Code)

Max Activating Token Index: 680

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0390. Min Act: -0.0001

Data Index: 853048 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0389. Min Act: -0.0001

Data Index: 738385 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0374. Min Act: -0.0001

Data Index: 600348 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0361. Min Act: -0.0001

Data Index: 726159 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1649921 (Python Code)

Max Activating Token Index: 730

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1612798 (Python Code)

Max Activating Token Index: 947

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0375. Min Act: -0.0001

Data Index: 391475 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0356. Min Act: -0.0001

Data Index: 809435 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1172820 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1162968 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0343. Min Act: -0.0001

Data Index: 17100 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0370. Min Act: -0.0001

Data Index: 793329 (C4 (Web Text))

Max Activating Token Index: 1020