Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 993 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3759. Min Act: -0.0001

Data Index: 199399 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3337. Min Act: -0.0001

Data Index: 1281350 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2672. Min Act: -0.0001

Data Index: 386882 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3187. Min Act: -0.0001

Data Index: 751985 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2901. Min Act: -0.0001

Data Index: 928363 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2811. Min Act: -0.0001

Data Index: 997757 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2812. Min Act: -0.0001

Data Index: 452994 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2596. Min Act: -0.0001

Data Index: 1321942 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2583. Min Act: -0.0001

Data Index: 999597 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2420. Min Act: -0.0001

Data Index: 165066 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2441. Min Act: -0.0001

Data Index: 195163 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2334. Min Act: -0.0001

Data Index: 936785 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1355087 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2280. Min Act: -0.0001

Data Index: 651080 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2438. Min Act: -0.0001

Data Index: 551834 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2415. Min Act: -0.0001

Data Index: 104423 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2590. Min Act: -0.0001

Data Index: 1144438 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2482. Min Act: -0.0001

Data Index: 603876 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2556. Min Act: -0.0001

Data Index: 138352 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2643. Min Act: -0.0001

Data Index: 140501 (C4 (Web Text))

Max Activating Token Index: 666