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

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

Neuron 301 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1075. Min Range: -3.1075

Max Act: 3.1075. Min Act: -0.0000

Data Index: 799411 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.3530. Min Act: -0.0000

Data Index: 339460 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.3577. Min Act: -0.0000

Data Index: 463557 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.2222. Min Act: -0.0000

Data Index: 44684 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.3118. Min Act: -0.0000

Data Index: 1151726 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.3093. Min Act: -0.0000

Data Index: 837199 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.2146. Min Act: -0.0000

Data Index: 1261466 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.1768. Min Act: -0.0000

Data Index: 314279 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.1476. Min Act: -0.0000

Data Index: 1256856 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.1484. Min Act: -0.0000

Data Index: 1280313 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.0852. Min Act: -0.0000

Data Index: 1127123 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.0803. Min Act: -0.0000

Data Index: 538041 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.0600. Min Act: -0.0000

Data Index: 410382 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 3.1075. Min Range: -3.1075

Max Act: 1.9413. Min Act: -0.0000

Data Index: 484491 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.0649. Min Act: -0.0000

Data Index: 565183 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.0045. Min Act: -0.0000

Data Index: 162640 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 3.1075. Min Range: -3.1075

Max Act: 1.9915. Min Act: -0.0000

Data Index: 542598 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 3.1075. Min Range: -3.1075

Max Act: 1.9663. Min Act: -0.0000

Data Index: 172867 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 3.1075. Min Range: -3.1075

Max Act: 2.0306. Min Act: -0.0000

Data Index: 1158143 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 3.1075. Min Range: -3.1075

Max Act: 1.8357. Min Act: -0.0000

Data Index: 465286 (C4 (Web Text))

Max Activating Token Index: 88