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

Dataset: The Pile

Neuron 593 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: 1.6932. Min Range: -1.6932

Max Act: 1.5931. Min Act: -0.0000

Data Index: 1523738 (The Pile)

Max Activating Token Index: 150

Text #1

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.6932. Min Act: -0.0000

Data Index: 475662 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1219018 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.3925. Min Act: -0.0000

Data Index: 1775447 (The Pile)

Max Activating Token Index: 677

Text #4

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.3112. Min Act: -0.0000

Data Index: 1086217 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.2946. Min Act: -0.0000

Data Index: 1696439 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1684781 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.4151. Min Act: -0.0000

Data Index: 719913 (The Pile)

Max Activating Token Index: 583

Text #8

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1045114 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1482161 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1604889 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1914933 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1961. Min Act: -0.0000

Data Index: 626180 (The Pile)

Max Activating Token Index: 525

Text #13

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1472243 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.2353. Min Act: -0.0000

Data Index: 157938 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1359250 (The Pile)

Max Activating Token Index: 598

Text #16

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1969077 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1818. Min Act: -0.0000

Data Index: 702170 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1961352 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 1.6932. Min Range: -1.6932

Max Act: 1.1056. Min Act: -0.0000

Data Index: 524119 (The Pile)

Max Activating Token Index: 793