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

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

Neuron 1193 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.5483. Min Act: -0.0000

Data Index: 560642 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1258070 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.1636. Min Act: -0.0000

Data Index: 1232928 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1255011 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.1480. Min Act: -0.0000

Data Index: 767691 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.0687. Min Act: -0.0000

Data Index: 141551 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.0025. Min Act: -0.0000

Data Index: 6666 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.0954. Min Act: -0.0000

Data Index: 474255 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1180122 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.0497. Min Act: -0.0000

Data Index: 69985 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.0038. Min Act: -0.0000

Data Index: 181099 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 1.5483. Min Range: -1.5483

Max Act: 0.9397. Min Act: -0.0000

Data Index: 176615 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.5483. Min Range: -1.5483

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1014726 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 1.5483. Min Range: -1.5483

Max Act: 1.0018. Min Act: -0.0000

Data Index: 547170 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 1.5483. Min Range: -1.5483

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1407932 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 1.5483. Min Range: -1.5483

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1329729 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 1.5483. Min Range: -1.5483

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1464362 (Python Code)

Max Activating Token Index: 748

Text #17

Max Range: 1.5483. Min Range: -1.5483

Max Act: 0.9297. Min Act: -0.0000

Data Index: 840196 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 1.5483. Min Range: -1.5483

Max Act: 0.8635. Min Act: -0.0000

Data Index: 150705 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 1.5483. Min Range: -1.5483

Max Act: 0.9093. Min Act: -0.0000

Data Index: 317552 (C4 (Web Text))

Max Activating Token Index: 100