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

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

Neuron 1396 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.7432. Min Act: -0.0001

Data Index: 313753 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.5203. Min Act: -0.0001

Data Index: 971117 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.7210. Min Act: -0.0002

Data Index: 1107996 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.5512. Min Act: -0.0001

Data Index: 141909 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.5006. Min Act: -0.0002

Data Index: 223599 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.1130. Min Act: -0.0002

Data Index: 1340971 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.3628. Min Act: -0.0001

Data Index: 505155 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.1477. Min Act: -0.0002

Data Index: 1235487 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.3430. Min Act: -0.0001

Data Index: 553236 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.4124. Min Act: -0.0002

Data Index: 448222 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.3666. Min Act: -0.0001

Data Index: 209276 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.2812. Min Act: -0.0001

Data Index: 468407 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.1996. Min Act: -0.0001

Data Index: 717001 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.1896. Min Act: -0.0002

Data Index: 959624 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.3697. Min Act: -0.0001

Data Index: 867897 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.3246. Min Act: -0.0001

Data Index: 846664 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.3531. Min Act: -0.0002

Data Index: 184877 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.2398. Min Act: -0.0001

Data Index: 131708 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.4733. Min Act: -0.0002

Data Index: 996119 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 1.7432. Min Range: -1.7432

Max Act: 1.2605. Min Act: -0.0002

Data Index: 1138163 (C4 (Web Text))

Max Activating Token Index: 409