Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 465 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5826. Min Range: -2.5826

Max Act: 2.5826. Min Act: -0.0000

Data Index: 32051 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.4855. Min Act: -0.0000

Data Index: 1043337 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.0187. Min Act: -0.0000

Data Index: 444470 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.1755. Min Act: -0.0000

Data Index: 631528 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 2.5826. Min Range: -2.5826

Max Act: 0.9547. Min Act: -0.0000

Data Index: 607193 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.0879. Min Act: -0.0000

Data Index: 736552 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.0862. Min Act: -0.0000

Data Index: 881771 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.1244. Min Act: -0.0000

Data Index: 704601 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.0511. Min Act: -0.0000

Data Index: 211861 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 2.5826. Min Range: -2.5826

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1299518 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.0726. Min Act: -0.0000

Data Index: 893288 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1170513 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.1752. Min Act: -0.0000

Data Index: 856700 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.2243. Min Act: -0.0000

Data Index: 960174 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 2.5826. Min Range: -2.5826

Max Act: 0.9493. Min Act: -0.0000

Data Index: 751421 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 2.5826. Min Range: -2.5826

Max Act: 1.1302. Min Act: -0.0000

Data Index: 417360 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 2.5826. Min Range: -2.5826

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1271116 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 2.5826. Min Range: -2.5826

Max Act: 0.9313. Min Act: -0.0000

Data Index: 134699 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 2.5826. Min Range: -2.5826

Max Act: 0.9942. Min Act: -0.0000

Data Index: 290110 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 2.5826. Min Range: -2.5826

Max Act: 0.9229. Min Act: -0.0000

Data Index: 65760 (C4 (Web Text))

Max Activating Token Index: 641