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

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

Neuron 4427 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1187319 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.8310. Min Act: -0.0000

Data Index: 216887 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7625. Min Act: -0.0000

Data Index: 208837 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7296. Min Act: -0.0000

Data Index: 304050 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7572. Min Act: -0.0000

Data Index: 980901 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7377. Min Act: -0.0000

Data Index: 181285 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7474. Min Act: -0.0000

Data Index: 174533 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7191. Min Act: -0.0000

Data Index: 419979 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6996. Min Act: -0.0000

Data Index: 619079 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6705. Min Act: -0.0001

Data Index: 428334 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6590. Min Act: -0.0000

Data Index: 440768 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6564. Min Act: -0.0000

Data Index: 726932 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1166509 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6513. Min Act: -0.0000

Data Index: 219973 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6218. Min Act: -0.0000

Data Index: 833669 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5855. Min Act: -0.0001

Data Index: 437382 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6859. Min Act: -0.0000

Data Index: 22672 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6734. Min Act: -0.0000

Data Index: 163682 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5964. Min Act: -0.0000

Data Index: 910491 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5750. Min Act: -0.0000

Data Index: 2380 (C4 (Web Text))

Max Activating Token Index: 560