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

Dataset: The Pile

Neuron 1374 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1160350 (The Pile)

Max Activating Token Index: 198

Text #1

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.0628. Min Act: -0.0000

Data Index: 488243 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.1155. Min Act: -0.0000

Data Index: 244547 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.0588. Min Act: -0.0000

Data Index: 1491795 (The Pile)

Max Activating Token Index: 25

Text #4

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9850. Min Act: -0.0000

Data Index: 367443 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9265. Min Act: -0.0000

Data Index: 266410 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1368559 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1327343 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1144765 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1329799 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1854231 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8956. Min Act: -0.0000

Data Index: 623908 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9082. Min Act: 0.0000

Data Index: 1192654 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1541001 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8992. Min Act: -0.0000

Data Index: 1740726 (The Pile)

Max Activating Token Index: 237

Text #15

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1679322 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8624. Min Act: -0.0000

Data Index: 561249 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9265. Min Act: 0.0000

Data Index: 1229983 (The Pile)

Max Activating Token Index: 167

Text #18

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8567. Min Act: 0.0000

Data Index: 1277269 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1670450 (The Pile)

Max Activating Token Index: 866