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

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

Neuron 783 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5003. Min Range: -2.5003

Max Act: 2.5003. Min Act: -0.0000

Data Index: 226115 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.9728. Min Act: -0.0000

Data Index: 458194 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.8265. Min Act: -0.0000

Data Index: 753468 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.4579. Min Act: -0.0000

Data Index: 387342 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.5931. Min Act: -0.0000

Data Index: 1112419 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.4773. Min Act: -0.0000

Data Index: 1200316 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.5143. Min Act: -0.0000

Data Index: 663755 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.4006. Min Act: -0.0000

Data Index: 293303 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.4786. Min Act: -0.0000

Data Index: 613695 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.5757. Min Act: -0.0000

Data Index: 840996 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.3491. Min Act: -0.0000

Data Index: 952247 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.3461. Min Act: -0.0000

Data Index: 460265 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.4781. Min Act: -0.0000

Data Index: 647326 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.4556. Min Act: -0.0000

Data Index: 143131 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1106578 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.2414. Min Act: -0.0000

Data Index: 418347 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.4035. Min Act: -0.0000

Data Index: 195977 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.2708. Min Act: -0.0000

Data Index: 623376 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.2098. Min Act: -0.0000

Data Index: 1072017 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.2066. Min Act: -0.0000

Data Index: 173930 (C4 (Web Text))

Max Activating Token Index: 126