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

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

Neuron 1926 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: 0.2909. Min Range: -0.2909

Max Act: 0.2717. Min Act: -0.0002

Data Index: 834115 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2629. Min Act: -0.0002

Data Index: 684198 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2775. Min Act: -0.0002

Data Index: 786059 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2694. Min Act: -0.0002

Data Index: 401792 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2678. Min Act: -0.0002

Data Index: 876308 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2606. Min Act: -0.0002

Data Index: 938163 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2657. Min Act: -0.0002

Data Index: 563273 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2909. Min Act: -0.0002

Data Index: 290300 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2642. Min Act: -0.0002

Data Index: 485402 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2513. Min Act: -0.0002

Data Index: 627430 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2532. Min Act: -0.0002

Data Index: 343876 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2450. Min Act: -0.0002

Data Index: 457820 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2513. Min Act: -0.0002

Data Index: 27795 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2599. Min Act: -0.0002

Data Index: 419064 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2497. Min Act: -0.0002

Data Index: 940783 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2438. Min Act: -0.0002

Data Index: 1109287 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2737. Min Act: -0.0002

Data Index: 779657 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2559. Min Act: -0.0002

Data Index: 1005083 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2374. Min Act: -0.0002

Data Index: 16106 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2403. Min Act: -0.0002

Data Index: 464092 (C4 (Web Text))

Max Activating Token Index: 933