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

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

Neuron 3494 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.5224. Min Act: -0.0000

Data Index: 162293 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.2682. Min Act: -0.0000

Data Index: 347667 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1686. Min Act: -0.0000

Data Index: 539699 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.2194. Min Act: -0.0000

Data Index: 1163206 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.2021. Min Act: -0.0000

Data Index: 30385 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1284171 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1858. Min Act: -0.0000

Data Index: 481291 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.2233. Min Act: -0.0000

Data Index: 67278 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1476. Min Act: -0.0000

Data Index: 1108059 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1389. Min Act: -0.0000

Data Index: 137072 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1340. Min Act: -0.0000

Data Index: 449128 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1305019 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1016952 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1019. Min Act: -0.0000

Data Index: 346309 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1147251 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0716. Min Act: -0.0000

Data Index: 204424 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1076021 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0954. Min Act: -0.0000

Data Index: 536863 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 1.5224. Min Range: -1.5224

Max Act: 0.9467. Min Act: -0.0000

Data Index: 193665 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 1.5224. Min Range: -1.5224

Max Act: 0.9364. Min Act: -0.0000

Data Index: 343297 (C4 (Web Text))

Max Activating Token Index: 724