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

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

Neuron 1379 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: 1.3837. Min Range: -1.3837

Max Act: 1.3837. Min Act: -0.0001

Data Index: 837171 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1945. Min Act: -0.0001

Data Index: 1207774 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2309. Min Act: -0.0001

Data Index: 912388 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1892. Min Act: -0.0001

Data Index: 494921 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2242. Min Act: -0.0001

Data Index: 972488 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2227. Min Act: -0.0001

Data Index: 317515 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.0794. Min Act: -0.0001

Data Index: 1224711 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1298. Min Act: -0.0001

Data Index: 164378 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1259. Min Act: -0.0001

Data Index: 18610 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1487. Min Act: -0.0001

Data Index: 193302 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1092. Min Act: -0.0001

Data Index: 529269 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1233. Min Act: -0.0001

Data Index: 328836 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1397. Min Act: -0.0001

Data Index: 90230 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1083. Min Act: -0.0001

Data Index: 562775 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.0702. Min Act: -0.0001

Data Index: 612774 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.0620. Min Act: -0.0001

Data Index: 294531 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.0623. Min Act: -0.0001

Data Index: 319000 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1461. Min Act: -0.0001

Data Index: 1147595 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.0424. Min Act: -0.0001

Data Index: 764730 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.9295. Min Act: -0.0001

Data Index: 1138335 (C4 (Web Text))

Max Activating Token Index: 234