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

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

Neuron 3054 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2342. Min Act: -0.0001

Data Index: 156525 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2214. Min Act: -0.0001

Data Index: 1057445 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2282. Min Act: -0.0001

Data Index: 493599 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2150. Min Act: -0.0001

Data Index: 493710 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2128. Min Act: -0.0001

Data Index: 1345544 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2037. Min Act: -0.0001

Data Index: 452769 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2025. Min Act: -0.0001

Data Index: 963533 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1998. Min Act: -0.0001

Data Index: 271870 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2002. Min Act: -0.0001

Data Index: 213345 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1917. Min Act: -0.0001

Data Index: 244337 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1905. Min Act: -0.0001

Data Index: 272216 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1959. Min Act: -0.0001

Data Index: 94749 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2005. Min Act: -0.0001

Data Index: 929537 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1935. Min Act: -0.0001

Data Index: 138112 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1920. Min Act: -0.0001

Data Index: 133709 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1031429 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1962. Min Act: -0.0001

Data Index: 911096 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1136385 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1332839 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1313291 (C4 (Web Text))

Max Activating Token Index: 802