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

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

Neuron 2561 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0002

Data Index: 914132 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0595. Min Act: -0.0002

Data Index: 455171 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0572. Min Act: -0.0002

Data Index: 27367 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0576. Min Act: -0.0002

Data Index: 995396 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1225509 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0555. Min Act: -0.0002

Data Index: 639708 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1305773 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0530. Min Act: -0.0002

Data Index: 56885 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0545. Min Act: -0.0002

Data Index: 351961 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1151024 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0541. Min Act: -0.0002

Data Index: 831260 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0561. Min Act: -0.0002

Data Index: 807659 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1248652 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0494. Min Act: -0.0002

Data Index: 385935 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1270246 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1142234 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1349399 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0523. Min Act: -0.0002

Data Index: 486404 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0515. Min Act: -0.0002

Data Index: 25075 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1166628 (C4 (Web Text))

Max Activating Token Index: 541