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

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

Neuron 2078 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: 1.5520. Min Range: -1.5520

Max Act: 1.5520. Min Act: -0.0000

Data Index: 338305 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.2524. Min Act: -0.0000

Data Index: 752450 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.1214. Min Act: -0.0000

Data Index: 481068 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 1.5520. Min Range: -1.5520

Max Act: 0.9849. Min Act: -0.0001

Data Index: 881734 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.0877. Min Act: -0.0001

Data Index: 504854 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.0184. Min Act: -0.0001

Data Index: 198047 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.0314. Min Act: -0.0000

Data Index: 468255 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.5520. Min Range: -1.5520

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1304845 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.0950. Min Act: -0.0000

Data Index: 904069 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.0598. Min Act: -0.0000

Data Index: 500870 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.0209. Min Act: -0.0000

Data Index: 69613 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 1.5520. Min Range: -1.5520

Max Act: 0.8757. Min Act: -0.0000

Data Index: 545459 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.5520. Min Range: -1.5520

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1356120 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.0490. Min Act: -0.0000

Data Index: 652222 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.5520. Min Range: -1.5520

Max Act: 0.9386. Min Act: -0.0001

Data Index: 647562 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.0171. Min Act: -0.0001

Data Index: 225204 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 1.5520. Min Range: -1.5520

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1249668 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.5520. Min Range: -1.5520

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1207079 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.5520. Min Range: -1.5520

Max Act: 1.0915. Min Act: -0.0001

Data Index: 173031 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 1.5520. Min Range: -1.5520

Max Act: 0.9449. Min Act: -0.0000

Data Index: 336776 (C4 (Web Text))

Max Activating Token Index: 939