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

Dataset: The Pile

Neuron 3391 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: 1.4469. Min Range: -1.4469

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1446173 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.3814. Min Act: -0.0000

Data Index: 518132 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.4097. Min Act: -0.0000

Data Index: 1955717 (The Pile)

Max Activating Token Index: 917

Text #3

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.2992. Min Act: -0.0000

Data Index: 875965 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.4469. Min Act: -0.0000

Data Index: 1296837 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1884680 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1965490 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1509325 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1042492 (The Pile)

Max Activating Token Index: 632

Text #9

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.2074. Min Act: -0.0000

Data Index: 979595 (The Pile)

Max Activating Token Index: 623

Text #10

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.2057. Min Act: -0.0000

Data Index: 582644 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.1419. Min Act: -0.0000

Data Index: 184731 (The Pile)

Max Activating Token Index: 689

Text #12

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.1268. Min Act: -0.0000

Data Index: 552183 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.1287. Min Act: -0.0000

Data Index: 391380 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.0624. Min Act: -0.0000

Data Index: 688959 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1910209 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.1199. Min Act: -0.0000

Data Index: 553596 (The Pile)

Max Activating Token Index: 907

Text #17

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.2045. Min Act: -0.0000

Data Index: 905986 (The Pile)

Max Activating Token Index: 797

Text #18

Max Range: 1.4469. Min Range: -1.4469

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1848920 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 1.4469. Min Range: -1.4469

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1892325 (The Pile)

Max Activating Token Index: 833