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

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

Neuron 1052 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1588531 (Python Code)

Max Activating Token Index: 875

Text #1

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1192. Min Act: -0.0000

Data Index: 443516 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1095. Min Act: -0.0000

Data Index: 70308 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0932. Min Act: -0.0000

Data Index: 739139 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1464668 (Python Code)

Max Activating Token Index: 981

Text #5

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0965. Min Act: -0.0000

Data Index: 864259 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1462456 (Python Code)

Max Activating Token Index: 973

Text #7

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0821. Min Act: -0.0000

Data Index: 827337 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0862. Min Act: -0.0000

Data Index: 93221 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1255243 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1496024 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1563703 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1492489 (Python Code)

Max Activating Token Index: 933

Text #13

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1561640 (Python Code)

Max Activating Token Index: 721

Text #14

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1409009 (Python Code)

Max Activating Token Index: 526

Text #15

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1303351 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0818. Min Act: -0.0000

Data Index: 340134 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1635294 (Python Code)

Max Activating Token Index: 716

Text #18

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0751. Min Act: -0.0000

Data Index: 798281 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1538280 (Python Code)

Max Activating Token Index: 707