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

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

Neuron 2551 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.5494. Min Act: -0.0002

Data Index: 605591 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.3626. Min Act: -0.0002

Data Index: 965665 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2873. Min Act: -0.0002

Data Index: 1149043 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2847. Min Act: -0.0002

Data Index: 365100 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2746. Min Act: -0.0002

Data Index: 1246984 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2357. Min Act: -0.0002

Data Index: 1239590 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2273. Min Act: -0.0002

Data Index: 696347 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2332. Min Act: -0.0002

Data Index: 366423 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2557. Min Act: -0.0002

Data Index: 122940 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2299. Min Act: -0.0002

Data Index: 741499 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2001. Min Act: -0.0002

Data Index: 319590 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2246. Min Act: -0.0002

Data Index: 455035 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2179. Min Act: -0.0002

Data Index: 55580 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2101. Min Act: -0.0002

Data Index: 1018178 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2023. Min Act: -0.0002

Data Index: 126020 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.2058. Min Act: -0.0002

Data Index: 294602 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.1766. Min Act: -0.0002

Data Index: 431391 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.1938. Min Act: -0.0002

Data Index: 59872 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.1805. Min Act: -0.0002

Data Index: 14214 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.1643. Min Act: -0.0002

Data Index: 512296 (C4 (Web Text))

Max Activating Token Index: 926