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

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

Neuron 29 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2237. Min Range: -2.2237

Max Act: 2.2237. Min Act: 0.0001

Data Index: 1569688 (Python Code)

Max Activating Token Index: 995

Text #1

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.9309. Min Act: 0.0001

Data Index: 1572189 (Python Code)

Max Activating Token Index: 540

Text #2

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.9200. Min Act: 0.0000

Data Index: 1503125 (Python Code)

Max Activating Token Index: 918

Text #3

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.9651. Min Act: -0.0000

Data Index: 1532367 (Python Code)

Max Activating Token Index: 483

Text #4

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.9207. Min Act: -0.0000

Data Index: 658338 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.8362. Min Act: 0.0001

Data Index: 1566096 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.7908. Min Act: 0.0000

Data Index: 1654155 (Python Code)

Max Activating Token Index: 1021

Text #7

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.7875. Min Act: 0.0000

Data Index: 1629552 (Python Code)

Max Activating Token Index: 723

Text #8

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.7645. Min Act: -0.0000

Data Index: 1375892 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.7609. Min Act: 0.0000

Data Index: 1630213 (Python Code)

Max Activating Token Index: 924

Text #10

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.7327. Min Act: 0.0000

Data Index: 1574974 (Python Code)

Max Activating Token Index: 775

Text #11

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.6289. Min Act: -0.0000

Data Index: 1583919 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.6051. Min Act: -0.0000

Data Index: 466418 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.5789. Min Act: 0.0001

Data Index: 1626244 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.5447. Min Act: -0.0000

Data Index: 1480979 (Python Code)

Max Activating Token Index: 655

Text #15

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.5399. Min Act: -0.0000

Data Index: 1410214 (Python Code)

Max Activating Token Index: 649

Text #16

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.5260. Min Act: -0.0000

Data Index: 694779 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.4949. Min Act: -0.0000

Data Index: 1633249 (Python Code)

Max Activating Token Index: 936

Text #18

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.4603. Min Act: 0.0000

Data Index: 1490347 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 2.2237. Min Range: -2.2237

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1510955 (Python Code)

Max Activating Token Index: 288