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

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

Neuron 4991 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: 3.8687. Min Range: -3.8687

Max Act: 3.8687. Min Act: -0.0002

Data Index: 124341 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.3558. Min Act: -0.0002

Data Index: 873968 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.4836. Min Act: -0.0002

Data Index: 1207134 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.1890. Min Act: -0.0002

Data Index: 1296375 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.2362. Min Act: -0.0002

Data Index: 68785 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.8674. Min Act: -0.0002

Data Index: 1007869 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.1242. Min Act: -0.0002

Data Index: 195251 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.7736. Min Act: -0.0002

Data Index: 1017389 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.7538. Min Act: -0.0002

Data Index: 48488 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.7201. Min Act: -0.0002

Data Index: 1002994 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.4803. Min Act: -0.0002

Data Index: 1041540 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.3576. Min Act: -0.0002

Data Index: 666593 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.3157. Min Act: -0.0002

Data Index: 917955 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.6376. Min Act: -0.0002

Data Index: 107625 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.6212. Min Act: -0.0002

Data Index: 1255542 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.5722. Min Act: -0.0002

Data Index: 764284 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.5678. Min Act: -0.0002

Data Index: 1007052 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.5634. Min Act: -0.0002

Data Index: 1004761 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.6700. Min Act: -0.0002

Data Index: 699257 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 3.8687. Min Range: -3.8687

Max Act: 2.6436. Min Act: -0.0002

Data Index: 864066 (C4 (Web Text))

Max Activating Token Index: 329