Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1045 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0088. Min Range: -1.0088

Max Act: 1.0088. Min Act: -0.0000

Data Index: 1361954 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1626349 (Python Code)

Max Activating Token Index: 324

Text #2

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1498086 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1425608 (Python Code)

Max Activating Token Index: 659

Text #4

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1589056 (Python Code)

Max Activating Token Index: 394

Text #5

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1543828 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1368623 (Python Code)

Max Activating Token Index: 842

Text #7

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1577910 (Python Code)

Max Activating Token Index: 115

Text #8

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1369463 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1577833 (Python Code)

Max Activating Token Index: 1015

Text #10

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1489689 (Python Code)

Max Activating Token Index: 579

Text #11

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1402279 (Python Code)

Max Activating Token Index: 812

Text #12

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1459273 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1484228 (Python Code)

Max Activating Token Index: 200

Text #14

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1531786 (Python Code)

Max Activating Token Index: 673

Text #15

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1425330 (Python Code)

Max Activating Token Index: 921

Text #16

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1379209 (Python Code)

Max Activating Token Index: 170

Text #17

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1620025 (Python Code)

Max Activating Token Index: 546

Text #18

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1515545 (Python Code)

Max Activating Token Index: 986

Text #19

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1513467 (Python Code)

Max Activating Token Index: 541