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

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

Neuron 432 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0654. Min Range: -1.0654

Max Act: 1.0654. Min Act: -0.0000

Data Index: 326131 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 1.0654. Min Range: -1.0654

Max Act: 1.0160. Min Act: -0.0000

Data Index: 665637 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.9343. Min Act: -0.0000

Data Index: 517717 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.9299. Min Act: -0.0000

Data Index: 693274 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.8753. Min Act: -0.0000

Data Index: 51929 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.8421. Min Act: -0.0000

Data Index: 360335 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1532291 (Python Code)

Max Activating Token Index: 1007

Text #7

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1610180 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7863. Min Act: -0.0000

Data Index: 793056 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7840. Min Act: -0.0000

Data Index: 5224 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1528375 (Python Code)

Max Activating Token Index: 941

Text #11

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1169362 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1649909 (Python Code)

Max Activating Token Index: 1017

Text #13

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1650200 (Python Code)

Max Activating Token Index: 697

Text #14

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7441. Min Act: -0.0000

Data Index: 205855 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7480. Min Act: -0.0000

Data Index: 532961 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1443122 (Python Code)

Max Activating Token Index: 1019

Text #17

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7684. Min Act: -0.0000

Data Index: 13958 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1059614 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7465. Min Act: -0.0000

Data Index: 121177 (C4 (Web Text))

Max Activating Token Index: 367