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

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

Neuron 5580 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.3944. Min Act: -0.0000

Data Index: 179942 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.1638. Min Act: -0.0000

Data Index: 1497900 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.2049. Min Act: -0.0000

Data Index: 1381793 (Python Code)

Max Activating Token Index: 607

Text #3

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.2585. Min Act: -0.0000

Data Index: 370305 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.1802. Min Act: -0.0000

Data Index: 1589362 (Python Code)

Max Activating Token Index: 124

Text #5

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1477210 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.2108. Min Act: -0.0000

Data Index: 49921 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1328126 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1613512 (Python Code)

Max Activating Token Index: 1001

Text #9

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1626161 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.1632. Min Act: -0.0000

Data Index: 517836 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1616077 (Python Code)

Max Activating Token Index: 323

Text #12

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1598342 (Python Code)

Max Activating Token Index: 405

Text #13

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1627742 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.0913. Min Act: -0.0000

Data Index: 556836 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.1631. Min Act: -0.0000

Data Index: 67573 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1190241 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1134744 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.0660. Min Act: -0.0000

Data Index: 1275702 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.3944. Min Range: -1.3944

Max Act: 1.0943. Min Act: -0.0000

Data Index: 957977 (C4 (Web Text))

Max Activating Token Index: 588