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

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

Neuron 2678 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1796. Min Act: -0.0000

Data Index: 214992 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1078176 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1359726 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1253. Min Act: -0.0000

Data Index: 754422 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1242. Min Act: -0.0000

Data Index: 958686 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1256368 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1154. Min Act: -0.0000

Data Index: 22854 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1151. Min Act: -0.0001

Data Index: 708677 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1357442 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1197060 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1108. Min Act: -0.0000

Data Index: 153704 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1174. Min Act: -0.0000

Data Index: 252729 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1196691 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0990. Min Act: -0.0000

Data Index: 839054 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0973. Min Act: -0.0000

Data Index: 485379 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0974. Min Act: -0.0000

Data Index: 78730 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1026. Min Act: -0.0000

Data Index: 344913 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0989. Min Act: -0.0001

Data Index: 659227 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.0984. Min Act: -0.0001

Data Index: 458874 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1018. Min Act: -0.0000

Data Index: 70365 (C4 (Web Text))

Max Activating Token Index: 989