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

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

Neuron 1988 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: 3.2892. Min Range: -3.2892

Max Act: 3.2892. Min Act: -0.0001

Data Index: 158051 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.3121. Min Act: -0.0001

Data Index: 431552 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.2954. Min Act: -0.0001

Data Index: 171826 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.2648. Min Act: -0.0001

Data Index: 547204 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.2632. Min Act: -0.0001

Data Index: 339400 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.0254. Min Act: -0.0001

Data Index: 675245 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.1941. Min Act: -0.0001

Data Index: 1062344 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.1162. Min Act: -0.0001

Data Index: 933222 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.0806. Min Act: -0.0001

Data Index: 1213845 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.0479. Min Act: -0.0001

Data Index: 303466 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.1520. Min Act: -0.0001

Data Index: 16378 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.0286. Min Act: -0.0001

Data Index: 246916 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 3.2892. Min Range: -3.2892

Max Act: 1.8044. Min Act: -0.0001

Data Index: 90597 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.0031. Min Act: -0.0001

Data Index: 71569 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.0100. Min Act: -0.0001

Data Index: 934516 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.0907. Min Act: -0.0001

Data Index: 1218211 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.2892. Min Range: -3.2892

Max Act: 1.9803. Min Act: -0.0001

Data Index: 283696 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 3.2892. Min Range: -3.2892

Max Act: 1.9759. Min Act: -0.0001

Data Index: 487245 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 3.2892. Min Range: -3.2892

Max Act: 2.0740. Min Act: -0.0001

Data Index: 601860 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 3.2892. Min Range: -3.2892

Max Act: 1.8323. Min Act: -0.0001

Data Index: 908264 (C4 (Web Text))

Max Activating Token Index: 828