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

Dataset: The Pile

Neuron 1078 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.9482. Min Act: -0.0000

Data Index: 35713 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1146876 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1410122 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1299202 (The Pile)

Max Activating Token Index: 483

Text #4

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6943. Min Act: -0.0000

Data Index: 659629 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7110. Min Act: -0.0000

Data Index: 742131 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6650. Min Act: -0.0000

Data Index: 49280 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1723889 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6714. Min Act: -0.0000

Data Index: 467508 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6628. Min Act: -0.0000

Data Index: 22163 (The Pile)

Max Activating Token Index: 240

Text #10

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6089. Min Act: -0.0000

Data Index: 701078 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1574167 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1927272 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1738641 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1753412 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6220. Min Act: -0.0000

Data Index: 800761 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1057222 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6869. Min Act: -0.0000

Data Index: 629777 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1187474 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1669836 (The Pile)

Max Activating Token Index: 368