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

Dataset: The Pile

Neuron 1465 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: 1.4259. Min Range: -1.4259

Max Act: 1.4259. Min Act: -0.0000

Data Index: 848334 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1168117 (The Pile)

Max Activating Token Index: 188

Text #2

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.1553. Min Act: -0.0000

Data Index: 167165 (The Pile)

Max Activating Token Index: 602

Text #3

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.0776. Min Act: -0.0000

Data Index: 1886567 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1483854 (The Pile)

Max Activating Token Index: 112

Text #5

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1012742 (The Pile)

Max Activating Token Index: 560

Text #6

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.9389. Min Act: -0.0000

Data Index: 479470 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.9415. Min Act: -0.0000

Data Index: 912784 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1875738 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.9528. Min Act: -0.0000

Data Index: 361199 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1920249 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1472666 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1356710 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.8922. Min Act: -0.0000

Data Index: 418319 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.9010. Min Act: -0.0000

Data Index: 196456 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1408082 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1862411 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1066524 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.8350. Min Act: -0.0000

Data Index: 743374 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 1.4259. Min Range: -1.4259

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1552507 (The Pile)

Max Activating Token Index: 527