Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 366 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2707. Min Range: -1.2707

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1070357 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9587. Min Act: -0.0000

Data Index: 551938 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 1.2707. Min Range: -1.2707

Max Act: 1.0282. Min Act: -0.0000

Data Index: 609630 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9546. Min Act: -0.0000

Data Index: 878141 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1154289 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1205099 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1192654 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9204. Min Act: -0.0000

Data Index: 778709 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1002709 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1283439 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8510. Min Act: -0.0000

Data Index: 821708 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1254136 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8767. Min Act: -0.0000

Data Index: 114218 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8744. Min Act: -0.0000

Data Index: 845306 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1215408 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8712. Min Act: -0.0000

Data Index: 515804 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1098275 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8352. Min Act: -0.0000

Data Index: 834851 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8865. Min Act: -0.0000

Data Index: 356731 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1339763 (C4 (Web Text))

Max Activating Token Index: 105