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

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

Neuron 1640 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: 3.0005. Min Range: -3.0005

Max Act: 2.3148. Min Act: -0.0002

Data Index: 1224456 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.4284. Min Act: -0.0003

Data Index: 638590 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.6073. Min Act: -0.0002

Data Index: 1174037 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.1705. Min Act: -0.0002

Data Index: 947730 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.2133. Min Act: -0.0002

Data Index: 1190674 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 3.0005. Min Range: -3.0005

Max Act: 3.0005. Min Act: -0.0003

Data Index: 464121 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.2648. Min Act: -0.0002

Data Index: 1122442 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.1357. Min Act: -0.0003

Data Index: 711539 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.0205. Min Act: -0.0002

Data Index: 382890 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.1184. Min Act: -0.0002

Data Index: 141369 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.2266. Min Act: -0.0002

Data Index: 673069 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 3.0005. Min Range: -3.0005

Max Act: 1.8513. Min Act: -0.0002

Data Index: 1313696 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.0005. Min Range: -3.0005

Max Act: 1.8908. Min Act: -0.0002

Data Index: 1343071 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.1523. Min Act: -0.0002

Data Index: 78549 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.2338. Min Act: -0.0002

Data Index: 130223 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.1727. Min Act: -0.0002

Data Index: 462576 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.1517. Min Act: -0.0002

Data Index: 952081 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.2358. Min Act: -0.0002

Data Index: 741963 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 3.0005. Min Range: -3.0005

Max Act: 2.1598. Min Act: -0.0002

Data Index: 718356 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 3.0005. Min Range: -3.0005

Max Act: 1.9355. Min Act: -0.0002

Data Index: 521763 (C4 (Web Text))

Max Activating Token Index: 41