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

Dataset: The Pile

Neuron 461 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.7296. Min Act: -0.0000

Data Index: 1011395 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.4152. Min Act: -0.0000

Data Index: 1314748 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.4611. Min Act: -0.0000

Data Index: 561553 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.4068. Min Act: -0.0000

Data Index: 1327513 (The Pile)

Max Activating Token Index: 470

Text #4

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1228368 (The Pile)

Max Activating Token Index: 485

Text #5

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.3832. Min Act: -0.0000

Data Index: 459408 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.2701. Min Act: -0.0000

Data Index: 1759828 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1936126 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.4199. Min Act: -0.0000

Data Index: 1671648 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.1253. Min Act: -0.0000

Data Index: 1516145 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1940581 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.2139. Min Act: -0.0000

Data Index: 579331 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1570981 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.3037. Min Act: -0.0000

Data Index: 569902 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1514622 (The Pile)

Max Activating Token Index: 634

Text #15

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1165632 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.3205. Min Act: -0.0000

Data Index: 1339994 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1441961 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1193023 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1480037 (The Pile)

Max Activating Token Index: 910