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

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

Neuron 2256 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.3976. Min Act: -0.0000

Data Index: 890023 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.1864. Min Act: -0.0000

Data Index: 208539 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.2949. Min Act: -0.0000

Data Index: 819435 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.1926. Min Act: -0.0000

Data Index: 754478 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.1285. Min Act: -0.0000

Data Index: 129362 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.2796. Min Act: -0.0000

Data Index: 1353438 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.1950. Min Act: -0.0000

Data Index: 924759 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.1612. Min Act: -0.0000

Data Index: 235294 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.1257. Min Act: -0.0000

Data Index: 936356 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.0920. Min Act: -0.0000

Data Index: 999715 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1312375 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1029484 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.0699. Min Act: -0.0000

Data Index: 421332 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1285027 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.0583. Min Act: -0.0000

Data Index: 552130 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.0396. Min Act: -0.0000

Data Index: 872398 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 1.3976. Min Range: -1.3976

Max Act: 0.9844. Min Act: -0.0000

Data Index: 978977 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.0339. Min Act: -0.0000

Data Index: 461490 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 1.3976. Min Range: -1.3976

Max Act: 0.9710. Min Act: -0.0000

Data Index: 237530 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.3976. Min Range: -1.3976

Max Act: 1.0245. Min Act: -0.0000

Data Index: 533376 (C4 (Web Text))

Max Activating Token Index: 65