Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 884 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1824. Min Range: -1.1824

Max Act: 1.1611. Min Act: -0.0000

Data Index: 483611 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 1.1824. Min Range: -1.1824

Max Act: 1.1776. Min Act: -0.0000

Data Index: 1418240 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 1.1824. Min Range: -1.1824

Max Act: 1.1371. Min Act: -0.0000

Data Index: 1080868 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 1.1824. Min Range: -1.1824

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1281460 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 1.1824. Min Range: -1.1824

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1322910 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.1824. Min Range: -1.1824

Max Act: 1.0828. Min Act: -0.0000

Data Index: 1412991 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 1.1824. Min Range: -1.1824

Max Act: 1.1824. Min Act: -0.0000

Data Index: 447502 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.1824. Min Range: -1.1824

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1059941 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.8468. Min Act: -0.0000

Data Index: 673247 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.8168. Min Act: 0.0001

Data Index: 1376385 (Python Code)

Max Activating Token Index: 481

Text #10

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.7225. Min Act: -0.0000

Data Index: 1466513 (Python Code)

Max Activating Token Index: 401

Text #11

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1619470 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.6697. Min Act: 0.0000

Data Index: 1448064 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.6250. Min Act: 0.0000

Data Index: 1590390 (Python Code)

Max Activating Token Index: 485

Text #14

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.6114. Min Act: 0.0001

Data Index: 1520141 (Python Code)

Max Activating Token Index: 789

Text #15

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.6280. Min Act: 0.0000

Data Index: 1608893 (Python Code)

Max Activating Token Index: 224

Text #16

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.5595. Min Act: 0.0000

Data Index: 1379516 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.5868. Min Act: 0.0001

Data Index: 1650240 (Python Code)

Max Activating Token Index: 47

Text #18

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1406584 (Python Code)

Max Activating Token Index: 689

Text #19

Max Range: 1.1824. Min Range: -1.1824

Max Act: 0.5452. Min Act: 0.0001

Data Index: 1570269 (Python Code)

Max Activating Token Index: 163