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

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

Neuron 5729 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8488. Min Range: -2.8488

Max Act: 2.8488. Min Act: -0.0000

Data Index: 684203 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 2.8488. Min Range: -2.8488

Max Act: 2.7671. Min Act: -0.0000

Data Index: 605129 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 2.8488. Min Range: -2.8488

Max Act: 2.6322. Min Act: -0.0000

Data Index: 1143507 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 2.8488. Min Range: -2.8488

Max Act: 2.5070. Min Act: -0.0000

Data Index: 1050772 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 2.8488. Min Range: -2.8488

Max Act: 2.1434. Min Act: -0.0000

Data Index: 332874 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 2.8488. Min Range: -2.8488

Max Act: 2.1356. Min Act: -0.0000

Data Index: 335629 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 2.8488. Min Range: -2.8488

Max Act: 2.0007. Min Act: -0.0000

Data Index: 457418 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 2.8488. Min Range: -2.8488

Max Act: 2.0286. Min Act: -0.0000

Data Index: 195197 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 2.8488. Min Range: -2.8488

Max Act: 2.0099. Min Act: -0.0000

Data Index: 194519 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 2.8488. Min Range: -2.8488

Max Act: 1.9912. Min Act: -0.0000

Data Index: 319607 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 2.8488. Min Range: -2.8488

Max Act: 1.7699. Min Act: -0.0000

Data Index: 1156511 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 2.8488. Min Range: -2.8488

Max Act: 1.9748. Min Act: -0.0000

Data Index: 106306 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 2.8488. Min Range: -2.8488

Max Act: 2.0858. Min Act: -0.0000

Data Index: 1604510 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 2.8488. Min Range: -2.8488

Max Act: 1.9711. Min Act: -0.0000

Data Index: 476949 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 2.8488. Min Range: -2.8488

Max Act: 1.8414. Min Act: -0.0000

Data Index: 903692 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 2.8488. Min Range: -2.8488

Max Act: 1.9252. Min Act: -0.0000

Data Index: 576799 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 2.8488. Min Range: -2.8488

Max Act: 1.9051. Min Act: -0.0000

Data Index: 1265597 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 2.8488. Min Range: -2.8488

Max Act: 1.8211. Min Act: -0.0000

Data Index: 26416 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 2.8488. Min Range: -2.8488

Max Act: 1.8489. Min Act: -0.0000

Data Index: 200354 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 2.8488. Min Range: -2.8488

Max Act: 1.8417. Min Act: -0.0000

Data Index: 945011 (C4 (Web Text))

Max Activating Token Index: 860