Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 763 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.5336. Min Act: -0.0001

Data Index: 736704 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.6032. Min Act: -0.0001

Data Index: 1321177 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.3660. Min Act: -0.0001

Data Index: 972680 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.2518. Min Act: -0.0001

Data Index: 1343508 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.1799. Min Act: -0.0001

Data Index: 218251 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.2065. Min Act: -0.0001

Data Index: 1258810 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.1355. Min Act: -0.0001

Data Index: 180182 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.1653. Min Act: -0.0001

Data Index: 582022 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.2637. Min Act: -0.0001

Data Index: 536495 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 1.6032. Min Range: -1.6032

Max Act: 0.9319. Min Act: -0.0001

Data Index: 1109168 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.0445. Min Act: -0.0001

Data Index: 293026 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.1651. Min Act: -0.0001

Data Index: 901992 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.1049. Min Act: -0.0001

Data Index: 1267672 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.0683. Min Act: -0.0001

Data Index: 428217 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.1422. Min Act: -0.0001

Data Index: 17687 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 1.6032. Min Range: -1.6032

Max Act: 0.9045. Min Act: -0.0001

Data Index: 1154854 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.0333. Min Act: -0.0001

Data Index: 46673 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 1.6032. Min Range: -1.6032

Max Act: 1.0033. Min Act: -0.0001

Data Index: 383663 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.6032. Min Range: -1.6032

Max Act: 0.9905. Min Act: -0.0001

Data Index: 646596 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 1.6032. Min Range: -1.6032

Max Act: 0.8714. Min Act: -0.0001

Data Index: 346842 (C4 (Web Text))

Max Activating Token Index: 755