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

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

Neuron 3254 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: 0.7066. Min Range: -0.7066

Max Act: 0.7066. Min Act: -0.0000

Data Index: 821877 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1318731 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5893. Min Act: -0.0000

Data Index: 902365 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1594333 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5795. Min Act: -0.0000

Data Index: 475077 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5685. Min Act: -0.0000

Data Index: 494544 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5290. Min Act: -0.0000

Data Index: 776440 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5696. Min Act: -0.0000

Data Index: 333068 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1032588 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1580311 (Python Code)

Max Activating Token Index: 343

Text #10

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4863. Min Act: -0.0000

Data Index: 316225 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1402738 (Python Code)

Max Activating Token Index: 652

Text #12

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4803. Min Act: -0.0000

Data Index: 636369 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4738. Min Act: -0.0000

Data Index: 396393 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1179326 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5299. Min Act: -0.0000

Data Index: 465045 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4635. Min Act: -0.0000

Data Index: 186250 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1607226 (Python Code)

Max Activating Token Index: 391

Text #18

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5047. Min Act: -0.0000

Data Index: 229095 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1040427 (C4 (Web Text))

Max Activating Token Index: 422