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

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

Neuron 1032 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.4748. Min Act: -0.0000

Data Index: 1353171 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1260947 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0251. Min Act: -0.0000

Data Index: 232030 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0210. Min Act: -0.0000

Data Index: 417378 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0767. Min Act: -0.0000

Data Index: 755532 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0034. Min Act: -0.0000

Data Index: 833842 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1125611 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9467. Min Act: -0.0000

Data Index: 931068 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9184. Min Act: -0.0000

Data Index: 597363 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8832. Min Act: -0.0000

Data Index: 183533 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8720. Min Act: -0.0000

Data Index: 725921 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1197306 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1292612 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8631. Min Act: -0.0000

Data Index: 614692 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8620. Min Act: -0.0000

Data Index: 404 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8470. Min Act: -0.0000

Data Index: 893533 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8562. Min Act: -0.0000

Data Index: 221949 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1151272 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8189. Min Act: -0.0000

Data Index: 563544 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.7853. Min Act: -0.0000

Data Index: 266037 (C4 (Web Text))

Max Activating Token Index: 831