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

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

Neuron 220 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: 2.4274. Min Range: -2.4274

Max Act: 2.4274. Min Act: -0.0000

Data Index: 41201 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.2972. Min Act: -0.0000

Data Index: 1537162 (Python Code)

Max Activating Token Index: 73

Text #2

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.1847. Min Act: -0.0000

Data Index: 1522445 (Python Code)

Max Activating Token Index: 209

Text #3

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.3104. Min Act: -0.0000

Data Index: 1411137 (Python Code)

Max Activating Token Index: 725

Text #4

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.0479. Min Act: -0.0000

Data Index: 1467144 (Python Code)

Max Activating Token Index: 145

Text #5

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.8343. Min Act: -0.0000

Data Index: 1530342 (Python Code)

Max Activating Token Index: 820

Text #6

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.7827. Min Act: -0.0000

Data Index: 1512037 (Python Code)

Max Activating Token Index: 965

Text #7

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.9689. Min Act: -0.0000

Data Index: 1376486 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.7305. Min Act: -0.0000

Data Index: 702580 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.7912. Min Act: -0.0000

Data Index: 1538122 (Python Code)

Max Activating Token Index: 591

Text #10

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.9844. Min Act: -0.0000

Data Index: 1539539 (Python Code)

Max Activating Token Index: 889

Text #11

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.6697. Min Act: -0.0000

Data Index: 1630004 (Python Code)

Max Activating Token Index: 577

Text #12

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.7736. Min Act: -0.0000

Data Index: 1554088 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.8279. Min Act: -0.0000

Data Index: 1525006 (Python Code)

Max Activating Token Index: 416

Text #14

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.7338. Min Act: -0.0000

Data Index: 1534211 (Python Code)

Max Activating Token Index: 605

Text #15

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.8158. Min Act: -0.0000

Data Index: 1505378 (Python Code)

Max Activating Token Index: 885

Text #16

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.5924. Min Act: -0.0000

Data Index: 1574058 (Python Code)

Max Activating Token Index: 135

Text #17

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.7240. Min Act: -0.0000

Data Index: 87569 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.6817. Min Act: -0.0000

Data Index: 841791 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.6672. Min Act: -0.0000

Data Index: 1444055 (Python Code)

Max Activating Token Index: 127