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

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

Neuron 4769 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: 0.1091. Min Range: -0.1091

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1347954 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1000. Min Act: -0.0002

Data Index: 42604 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0962. Min Act: -0.0002

Data Index: 185027 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0822. Min Act: -0.0002

Data Index: 195513 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1048725 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0876. Min Act: -0.0002

Data Index: 248689 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0870. Min Act: -0.0002

Data Index: 633766 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0905. Min Act: -0.0002

Data Index: 403124 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1094069 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0841. Min Act: -0.0002

Data Index: 443527 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0780. Min Act: -0.0002

Data Index: 393161 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0787. Min Act: -0.0002

Data Index: 951818 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0821. Min Act: -0.0002

Data Index: 191271 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0779. Min Act: -0.0002

Data Index: 814577 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0742. Min Act: -0.0002

Data Index: 601481 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0795. Min Act: -0.0002

Data Index: 564935 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0796. Min Act: -0.0002

Data Index: 338980 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0745. Min Act: -0.0002

Data Index: 874683 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0818. Min Act: -0.0002

Data Index: 764329 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0728. Min Act: -0.0002

Data Index: 910774 (C4 (Web Text))

Max Activating Token Index: 723