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

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

Neuron 3711 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2550. Min Range: -1.2550

Max Act: 1.2217. Min Act: -0.0000

Data Index: 283461 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 1.2550. Min Range: -1.2550

Max Act: 1.2550. Min Act: -0.0000

Data Index: 477297 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 1.2550. Min Range: -1.2550

Max Act: 1.1413. Min Act: -0.0000

Data Index: 306919 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 1.2550. Min Range: -1.2550

Max Act: 1.1417. Min Act: -0.0000

Data Index: 395574 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.2550. Min Range: -1.2550

Max Act: 1.0022. Min Act: -0.0000

Data Index: 650318 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 1.2550. Min Range: -1.2550

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1019275 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 1.2550. Min Range: -1.2550

Max Act: 1.1259. Min Act: -0.0000

Data Index: 428948 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 1.2550. Min Range: -1.2550

Max Act: 1.0751. Min Act: -0.0000

Data Index: 343288 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 1.2550. Min Range: -1.2550

Max Act: 1.0229. Min Act: -0.0000

Data Index: 691337 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.9738. Min Act: -0.0000

Data Index: 772506 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1316248 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1087159 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.9655. Min Act: -0.0000

Data Index: 666679 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.9602. Min Act: -0.0000

Data Index: 598435 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.9383. Min Act: -0.0000

Data Index: 14139 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.9265. Min Act: -0.0000

Data Index: 944065 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.9345. Min Act: -0.0000

Data Index: 376596 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.8281. Min Act: -0.0000

Data Index: 312694 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.8164. Min Act: -0.0000

Data Index: 916448 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.2550. Min Range: -1.2550

Max Act: 0.8445. Min Act: -0.0000

Data Index: 743065 (C4 (Web Text))

Max Activating Token Index: 596