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

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

Neuron 5595 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: 0.7571. Min Range: -0.7571

Max Act: 0.7180. Min Act: -0.0001

Data Index: 434672 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7166. Min Act: -0.0001

Data Index: 384599 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7571. Min Act: -0.0001

Data Index: 1095470 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6947. Min Act: -0.0001

Data Index: 489156 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6655. Min Act: -0.0001

Data Index: 466917 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5484. Min Act: -0.0001

Data Index: 1296395 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7444. Min Act: -0.0001

Data Index: 251945 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6556. Min Act: -0.0001

Data Index: 216707 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5703. Min Act: -0.0001

Data Index: 454669 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6636. Min Act: -0.0001

Data Index: 798791 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5615. Min Act: -0.0001

Data Index: 536110 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5873. Min Act: -0.0001

Data Index: 1156889 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6602. Min Act: -0.0001

Data Index: 896658 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6944. Min Act: -0.0001

Data Index: 102223 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6419. Min Act: -0.0001

Data Index: 701687 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6311. Min Act: -0.0001

Data Index: 653906 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6235. Min Act: -0.0001

Data Index: 1324395 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6459. Min Act: -0.0001

Data Index: 566364 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6274. Min Act: -0.0001

Data Index: 1272865 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6433. Min Act: -0.0001

Data Index: 546728 (C4 (Web Text))

Max Activating Token Index: 471