Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 692 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1205011 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1958. Min Act: -0.0000

Data Index: 461362 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1893. Min Act: -0.0000

Data Index: 90436 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1748. Min Act: -0.0001

Data Index: 127085 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1688. Min Act: -0.0000

Data Index: 51270 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1783. Min Act: -0.0000

Data Index: 557399 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1651. Min Act: -0.0000

Data Index: 506620 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1720. Min Act: -0.0000

Data Index: 901693 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1771. Min Act: -0.0000

Data Index: 625225 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1621. Min Act: -0.0001

Data Index: 485519 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1627. Min Act: -0.0001

Data Index: 204947 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1617. Min Act: -0.0000

Data Index: 814118 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1580. Min Act: -0.0000

Data Index: 796716 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1503. Min Act: -0.0000

Data Index: 414634 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1086013 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1523. Min Act: -0.0000

Data Index: 182394 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1588. Min Act: -0.0001

Data Index: 453730 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1496. Min Act: -0.0000

Data Index: 819043 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1340184 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1008244 (C4 (Web Text))

Max Activating Token Index: 742