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

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

Neuron 4665 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: 0.2048. Min Range: -0.2048

Max Act: 0.2048. Min Act: -0.0000

Data Index: 678642 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1019367 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.2014. Min Act: -0.0001

Data Index: 860069 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1813. Min Act: -0.0000

Data Index: 85172 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1660. Min Act: -0.0000

Data Index: 806295 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1541. Min Act: -0.0000

Data Index: 199204 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1645. Min Act: -0.0000

Data Index: 681567 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1132629 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1048129 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1505. Min Act: -0.0000

Data Index: 741430 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1581. Min Act: -0.0000

Data Index: 719452 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1409. Min Act: -0.0000

Data Index: 983572 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1497. Min Act: -0.0000

Data Index: 696063 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1340. Min Act: -0.0000

Data Index: 584143 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1070583 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1409. Min Act: -0.0000

Data Index: 757098 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1400. Min Act: -0.0001

Data Index: 356328 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1337608 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1391. Min Act: -0.0000

Data Index: 702686 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1372. Min Act: -0.0000

Data Index: 246102 (C4 (Web Text))

Max Activating Token Index: 834