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

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

Neuron 449 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5482. Min Act: -0.0000

Data Index: 1307733 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5996. Min Act: -0.0000

Data Index: 139652 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.5072. Min Act: -0.0001

Data Index: 217051 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.4096. Min Act: -0.0000

Data Index: 1354020 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.3766. Min Act: -0.0000

Data Index: 1652289 (Python Code)

Max Activating Token Index: 469

Text #5

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.4497. Min Act: -0.0000

Data Index: 1438707 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.2873. Min Act: -0.0001

Data Index: 1335637 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.3282. Min Act: -0.0000

Data Index: 1571873 (Python Code)

Max Activating Token Index: 801

Text #8

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.3348. Min Act: -0.0000

Data Index: 1263060 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.2827. Min Act: -0.0000

Data Index: 1071089 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.2268. Min Act: -0.0000

Data Index: 389360 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.2309. Min Act: -0.0001

Data Index: 1050387 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.2637. Min Act: -0.0000

Data Index: 403088 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.1491. Min Act: -0.0000

Data Index: 1056435 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.1045. Min Act: -0.0000

Data Index: 328957 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.2334. Min Act: -0.0001

Data Index: 1022137 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.2043. Min Act: -0.0001

Data Index: 113172 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.1316. Min Act: -0.0001

Data Index: 1504965 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.3026. Min Act: -0.0001

Data Index: 1309517 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.5996. Min Range: -1.5996

Max Act: 1.1903. Min Act: -0.0000

Data Index: 831989 (C4 (Web Text))

Max Activating Token Index: 662