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

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

Neuron 4527 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.8483. Min Act: -0.0000

Data Index: 1469348 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.6134. Min Act: -0.0000

Data Index: 1656707 (Python Code)

Max Activating Token Index: 110

Text #2

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.4565. Min Act: -0.0000

Data Index: 1483868 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.2466. Min Act: -0.0000

Data Index: 1524253 (Python Code)

Max Activating Token Index: 828

Text #4

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.1974. Min Act: -0.0000

Data Index: 1483351 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.1381. Min Act: -0.0000

Data Index: 1594447 (Python Code)

Max Activating Token Index: 210

Text #6

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.1903. Min Act: -0.0000

Data Index: 1295503 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.1702. Min Act: -0.0000

Data Index: 1532760 (Python Code)

Max Activating Token Index: 784

Text #8

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.0587. Min Act: -0.0000

Data Index: 1655036 (Python Code)

Max Activating Token Index: 694

Text #9

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.2751. Min Act: -0.0000

Data Index: 1478473 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.2680. Min Act: -0.0000

Data Index: 1517119 (Python Code)

Max Activating Token Index: 149

Text #11

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.2484. Min Act: -0.0000

Data Index: 1424397 (Python Code)

Max Activating Token Index: 451

Text #12

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.1066. Min Act: -0.0000

Data Index: 1575515 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.1143. Min Act: -0.0000

Data Index: 373558 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 2.8483. Min Range: -2.8483

Max Act: 1.8822. Min Act: -0.0000

Data Index: 1655289 (Python Code)

Max Activating Token Index: 188

Text #15

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.0823. Min Act: -0.0000

Data Index: 1525299 (Python Code)

Max Activating Token Index: 191

Text #16

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.0914. Min Act: -0.0000

Data Index: 1655146 (Python Code)

Max Activating Token Index: 649

Text #17

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.1977. Min Act: -0.0000

Data Index: 1560498 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.0732. Min Act: -0.0000

Data Index: 1365141 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 2.8483. Min Range: -2.8483

Max Act: 2.1618. Min Act: -0.0000

Data Index: 1547035 (Python Code)

Max Activating Token Index: 694