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

Dataset: The Pile

Neuron 1014 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: 1.7969. Min Range: -1.7969

Max Act: 1.7969. Min Act: -0.0000

Data Index: 1659343 (The Pile)

Max Activating Token Index: 956

Text #1

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.6176. Min Act: -0.0000

Data Index: 1126175 (The Pile)

Max Activating Token Index: 526

Text #2

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.4007. Min Act: -0.0000

Data Index: 1858288 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1383200 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.3410. Min Act: -0.0000

Data Index: 1841365 (The Pile)

Max Activating Token Index: 485

Text #5

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.3056. Min Act: -0.0000

Data Index: 490889 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.4262. Min Act: -0.0000

Data Index: 390350 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1462520 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.2150. Min Act: -0.0000

Data Index: 1931645 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.1425. Min Act: -0.0000

Data Index: 209593 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1193691 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1283516 (The Pile)

Max Activating Token Index: 340

Text #12

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.1155. Min Act: -0.0000

Data Index: 134805 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.1051. Min Act: -0.0000

Data Index: 325313 (The Pile)

Max Activating Token Index: 174

Text #14

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1070632 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 1.7969. Min Range: -1.7969

Max Act: 1.0056. Min Act: -0.0000

Data Index: 152821 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 1.7969. Min Range: -1.7969

Max Act: 0.9143. Min Act: -0.0000

Data Index: 909265 (The Pile)

Max Activating Token Index: 99

Text #17

Max Range: 1.7969. Min Range: -1.7969

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1423525 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 1.7969. Min Range: -1.7969

Max Act: 0.8372. Min Act: -0.0000

Data Index: 659282 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 1.7969. Min Range: -1.7969

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1221908 (The Pile)

Max Activating Token Index: 371