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

Dataset: The Pile

Neuron 2993 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: 0.3752. Min Range: -0.3752

Max Act: 0.3752. Min Act: -0.0000

Data Index: 280674 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2769. Min Act: -0.0000

Data Index: 508234 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1671316 (The Pile)

Max Activating Token Index: 509

Text #3

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1419318 (The Pile)

Max Activating Token Index: 768

Text #4

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2165. Min Act: -0.0000

Data Index: 562997 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1703. Min Act: -0.0000

Data Index: 536367 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1141815 (The Pile)

Max Activating Token Index: 919

Text #7

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1363. Min Act: -0.0000

Data Index: 297668 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1452. Min Act: -0.0000

Data Index: 564326 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1974696 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1243. Min Act: -0.0000

Data Index: 935298 (The Pile)

Max Activating Token Index: 129

Text #11

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1188777 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1355. Min Act: -0.0000

Data Index: 455186 (The Pile)

Max Activating Token Index: 304

Text #13

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1259. Min Act: -0.0000

Data Index: 672612 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1723728 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1822412 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1221. Min Act: -0.0000

Data Index: 941016 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1278. Min Act: -0.0000

Data Index: 884847 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1874593 (The Pile)

Max Activating Token Index: 899

Text #19

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1643747 (The Pile)

Max Activating Token Index: 844