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

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

Neuron 3574 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1565. Min Range: -1.1565

Max Act: 1.0368. Min Act: -0.0000

Data Index: 411356 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 1.1565. Min Range: -1.1565

Max Act: 1.1556. Min Act: -0.0000

Data Index: 1338787 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 1.1565. Min Range: -1.1565

Max Act: 1.0912. Min Act: -0.0000

Data Index: 973708 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 1.1565. Min Range: -1.1565

Max Act: 1.0797. Min Act: -0.0000

Data Index: 284699 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.1565. Min Range: -1.1565

Max Act: 1.1565. Min Act: -0.0000

Data Index: 425901 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.1565. Min Range: -1.1565

Max Act: 1.0322. Min Act: -0.0000

Data Index: 899255 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.1565. Min Range: -1.1565

Max Act: 1.0860. Min Act: -0.0000

Data Index: 877291 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.9529. Min Act: -0.0000

Data Index: 349217 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1009691 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.9457. Min Act: -0.0000

Data Index: 24142 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.9358. Min Act: -0.0000

Data Index: 867280 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1204001 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.9122. Min Act: -0.0000

Data Index: 342605 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1026054 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.8776. Min Act: -0.0000

Data Index: 296706 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.7839. Min Act: -0.0000

Data Index: 713024 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.7881. Min Act: -0.0000

Data Index: 967308 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1251460 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.6433. Min Act: -0.0000

Data Index: 780330 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.1565. Min Range: -1.1565

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1278007 (C4 (Web Text))

Max Activating Token Index: 50