Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1441 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1065. Min Act: -0.0002

Data Index: 890101 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1010539 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0986. Min Act: -0.0002

Data Index: 290611 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1346421 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1061867 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1351990 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0954. Min Act: -0.0002

Data Index: 903900 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0966. Min Act: -0.0002

Data Index: 892908 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1146296 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0935. Min Act: -0.0002

Data Index: 567762 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1267710 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0885. Min Act: -0.0002

Data Index: 295892 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0910. Min Act: -0.0002

Data Index: 329429 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0917. Min Act: -0.0002

Data Index: 893013 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0903. Min Act: -0.0002

Data Index: 525111 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1320124 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1351863 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0886. Min Act: -0.0002

Data Index: 987737 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0911. Min Act: -0.0002

Data Index: 105538 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0870. Min Act: -0.0002

Data Index: 945989 (C4 (Web Text))

Max Activating Token Index: 302