Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3837 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.9579. Min Act: -0.0001

Data Index: 1632728 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.8908. Min Act: -0.0001

Data Index: 1629569 (Python Code)

Max Activating Token Index: 297

Text #2

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.7737. Min Act: -0.0001

Data Index: 1576220 (Python Code)

Max Activating Token Index: 104

Text #3

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.7138. Min Act: -0.0001

Data Index: 1502255 (Python Code)

Max Activating Token Index: 185

Text #4

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6613. Min Act: -0.0001

Data Index: 1554863 (Python Code)

Max Activating Token Index: 892

Text #5

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.5901. Min Act: -0.0001

Data Index: 1623086 (Python Code)

Max Activating Token Index: 608

Text #6

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.7497. Min Act: -0.0001

Data Index: 1627523 (Python Code)

Max Activating Token Index: 515

Text #7

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6915. Min Act: -0.0001

Data Index: 1474429 (Python Code)

Max Activating Token Index: 557

Text #8

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6692. Min Act: -0.0001

Data Index: 1514175 (Python Code)

Max Activating Token Index: 340

Text #9

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.5912. Min Act: -0.0001

Data Index: 1482878 (Python Code)

Max Activating Token Index: 571

Text #10

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6238. Min Act: -0.0001

Data Index: 1566039 (Python Code)

Max Activating Token Index: 462

Text #11

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.7220. Min Act: -0.0001

Data Index: 1563607 (Python Code)

Max Activating Token Index: 732

Text #12

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6653. Min Act: -0.0001

Data Index: 1409784 (Python Code)

Max Activating Token Index: 603

Text #13

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6734. Min Act: -0.0001

Data Index: 1610077 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6208. Min Act: -0.0001

Data Index: 1383457 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.5559. Min Act: -0.0001

Data Index: 1462203 (Python Code)

Max Activating Token Index: 826

Text #16

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6417. Min Act: -0.0001

Data Index: 1483923 (Python Code)

Max Activating Token Index: 514

Text #17

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6359. Min Act: -0.0001

Data Index: 1521277 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6741. Min Act: -0.0001

Data Index: 1501433 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 1.9579. Min Range: -1.9579

Max Act: 1.6271. Min Act: -0.0001

Data Index: 1642056 (Python Code)

Max Activating Token Index: 920