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

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

Neuron 4327 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: 0.7217. Min Range: -0.7217

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1638253 (Python Code)

Max Activating Token Index: 888

Text #1

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1361471 (Python Code)

Max Activating Token Index: 649

Text #2

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4961. Min Act: -0.0000

Data Index: 948346 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1079297 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4517. Min Act: -0.0000

Data Index: 49091 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1654392 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4667. Min Act: -0.0000

Data Index: 309926 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4812. Min Act: -0.0000

Data Index: 919465 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4649. Min Act: -0.0000

Data Index: 433912 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4956. Min Act: -0.0000

Data Index: 964445 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4789. Min Act: -0.0000

Data Index: 123426 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1393394 (Python Code)

Max Activating Token Index: 765

Text #12

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1495289 (Python Code)

Max Activating Token Index: 813

Text #13

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1470589 (Python Code)

Max Activating Token Index: 958

Text #14

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1489545 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1247540 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4115. Min Act: -0.0000

Data Index: 544512 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1657059 (Python Code)

Max Activating Token Index: 796

Text #18

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1049349 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1361492 (Python Code)

Max Activating Token Index: 238