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

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

Neuron 315 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.2925. Min Act: -0.0000

Data Index: 556551 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.1657. Min Act: -0.0000

Data Index: 533973 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9711. Min Act: -0.0000

Data Index: 788901 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1336501 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9337. Min Act: -0.0000

Data Index: 201322 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8686. Min Act: -0.0000

Data Index: 523985 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8716. Min Act: -0.0000

Data Index: 544515 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1007338 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1008908 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1231850 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1308424 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8625. Min Act: -0.0000

Data Index: 817356 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1279830 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8124. Min Act: -0.0000

Data Index: 752820 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.7429. Min Act: -0.0000

Data Index: 563210 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.7666. Min Act: -0.0000

Data Index: 436080 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1351122 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.7827. Min Act: -0.0000

Data Index: 550613 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.7581. Min Act: -0.0000

Data Index: 769878 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1338968 (C4 (Web Text))

Max Activating Token Index: 76