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

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

Neuron 1928 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0002

Data Index: 254840 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0720. Min Act: -0.0002

Data Index: 432512 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0709. Min Act: -0.0002

Data Index: 390372 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0675. Min Act: -0.0002

Data Index: 146049 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1143474 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0640. Min Act: -0.0002

Data Index: 544123 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0650. Min Act: -0.0002

Data Index: 251089 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1185972 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0625. Min Act: -0.0002

Data Index: 653632 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0632. Min Act: -0.0002

Data Index: 94504 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0563. Min Act: -0.0002

Data Index: 501269 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0604. Min Act: -0.0002

Data Index: 691694 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1046763 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0502. Min Act: -0.0002

Data Index: 73096 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0584. Min Act: -0.0002

Data Index: 798121 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0647. Min Act: -0.0002

Data Index: 521562 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1254500 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0599. Min Act: -0.0002

Data Index: 71856 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0594. Min Act: -0.0002

Data Index: 435351 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1194722 (C4 (Web Text))

Max Activating Token Index: 937