Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2645 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1049480 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.2133. Min Act: -0.0001

Data Index: 386375 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.2003. Min Act: -0.0001

Data Index: 111615 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.2165. Min Act: -0.0000

Data Index: 734146 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.2018. Min Act: -0.0000

Data Index: 495863 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1970. Min Act: -0.0000

Data Index: 707210 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1971. Min Act: -0.0001

Data Index: 8792 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1940. Min Act: -0.0001

Data Index: 39441 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1876. Min Act: -0.0000

Data Index: 424829 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1812. Min Act: -0.0001

Data Index: 519582 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1764. Min Act: -0.0000

Data Index: 559131 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1747. Min Act: -0.0000

Data Index: 94786 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1742. Min Act: -0.0000

Data Index: 315776 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1737. Min Act: -0.0000

Data Index: 499511 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1005725 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1037370 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1682. Min Act: -0.0000

Data Index: 1292658 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1738. Min Act: -0.0000

Data Index: 110293 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1186709 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1628. Min Act: -0.0001

Data Index: 886190 (C4 (Web Text))

Max Activating Token Index: 580