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

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

Neuron 3520 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.2260. Min Act: -0.0001

Data Index: 629801 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.2220. Min Act: -0.0001

Data Index: 173191 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1920. Min Act: -0.0001

Data Index: 434823 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1876. Min Act: -0.0001

Data Index: 954031 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1864. Min Act: -0.0001

Data Index: 284290 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1801. Min Act: -0.0001

Data Index: 428756 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1751. Min Act: -0.0001

Data Index: 1024353 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1334709 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1723. Min Act: -0.0001

Data Index: 63605 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1626. Min Act: -0.0001

Data Index: 254531 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1678. Min Act: -0.0001

Data Index: 806308 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1568. Min Act: -0.0001

Data Index: 927854 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1606. Min Act: -0.0001

Data Index: 332096 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1520. Min Act: -0.0001

Data Index: 1180286 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1588. Min Act: -0.0001

Data Index: 335681 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1094898 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1579. Min Act: -0.0001

Data Index: 281276 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1576. Min Act: -0.0001

Data Index: 255773 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1477. Min Act: -0.0001

Data Index: 678775 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1438. Min Act: -0.0001

Data Index: 323772 (C4 (Web Text))

Max Activating Token Index: 224