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

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

Neuron 3330 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: 1.6012. Min Range: -1.6012

Max Act: 1.6012. Min Act: -0.0000

Data Index: 94098 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.3257. Min Act: -0.0000

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.1915. Min Act: -0.0000

Data Index: 667296 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.2703. Min Act: -0.0000

Data Index: 698190 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.2791. Min Act: -0.0000

Data Index: 536202 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.1794. Min Act: -0.0000

Data Index: 984752 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.1780. Min Act: -0.0000

Data Index: 466042 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1630049 (Python Code)

Max Activating Token Index: 730

Text #8

Max Range: 1.6012. Min Range: -1.6012

Max Act: 0.9884. Min Act: -0.0000

Data Index: 1521902 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.1628. Min Act: -0.0000

Data Index: 857865 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.1432. Min Act: -0.0000

Data Index: 435935 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1524852 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.1275. Min Act: -0.0000

Data Index: 121429 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1045080 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.0252. Min Act: -0.0000

Data Index: 584469 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1472511 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1549018 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1452839 (Python Code)

Max Activating Token Index: 143

Text #18

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.0235. Min Act: -0.0000

Data Index: 1602817 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 1.6012. Min Range: -1.6012

Max Act: 0.9967. Min Act: -0.0000

Data Index: 325855 (C4 (Web Text))

Max Activating Token Index: 728