Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 916 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.9354. Min Act: -0.0001

Data Index: 1090527 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.9280. Min Act: -0.0001

Data Index: 1165563 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.8582. Min Act: -0.0001

Data Index: 1036480 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6797. Min Act: -0.0001

Data Index: 299911 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.7214. Min Act: -0.0001

Data Index: 265047 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6751. Min Act: -0.0001

Data Index: 882881 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6656. Min Act: -0.0001

Data Index: 323224 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.7221. Min Act: -0.0001

Data Index: 635471 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6309. Min Act: -0.0001

Data Index: 1237414 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6526. Min Act: -0.0001

Data Index: 1306988 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6248. Min Act: -0.0001

Data Index: 257847 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6245. Min Act: -0.0001

Data Index: 888509 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.7003. Min Act: -0.0001

Data Index: 998358 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6555. Min Act: -0.0001

Data Index: 131378 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6402. Min Act: -0.0001

Data Index: 114834 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6298. Min Act: -0.0001

Data Index: 865903 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.5901. Min Act: -0.0001

Data Index: 1350528 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.5470. Min Act: -0.0001

Data Index: 479597 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.5834. Min Act: -0.0001

Data Index: 344735 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.5293. Min Act: -0.0001

Data Index: 617743 (C4 (Web Text))

Max Activating Token Index: 251