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

Dataset: The Pile

Neuron 2471 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.7558. Min Act: -0.0000

Data Index: 1676836 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.6025. Min Act: -0.0000

Data Index: 955608 (The Pile)

Max Activating Token Index: 915

Text #2

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.7142. Min Act: -0.0000

Data Index: 1667012 (The Pile)

Max Activating Token Index: 598

Text #3

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.5715. Min Act: -0.0000

Data Index: 1934220 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.7520. Min Act: -0.0000

Data Index: 1642164 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.2196. Min Act: -0.0000

Data Index: 1349566 (The Pile)

Max Activating Token Index: 927

Text #6

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.5518. Min Act: -0.0000

Data Index: 1060902 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.6560. Min Act: -0.0000

Data Index: 1458127 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.0754. Min Act: -0.0000

Data Index: 1569037 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.2539. Min Act: -0.0000

Data Index: 323039 (The Pile)

Max Activating Token Index: 563

Text #10

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.5846. Min Act: -0.0000

Data Index: 1856150 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.2150. Min Act: -0.0000

Data Index: 1829823 (The Pile)

Max Activating Token Index: 741

Text #12

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.8187. Min Act: -0.0000

Data Index: 525652 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.0979. Min Act: -0.0000

Data Index: 75838 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.1318. Min Act: -0.0000

Data Index: 547526 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.2305. Min Act: -0.0000

Data Index: 1219959 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.0769. Min Act: -0.0000

Data Index: 667139 (The Pile)

Max Activating Token Index: 272

Text #17

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.1037. Min Act: -0.0000

Data Index: 1519522 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 11.8187. Min Range: -11.8187

Max Act: 10.9228. Min Act: -0.0000

Data Index: 1371098 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 11.8187. Min Range: -11.8187

Max Act: 11.1460. Min Act: -0.0000

Data Index: 1511239 (The Pile)

Max Activating Token Index: 887