Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 617 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.5818. Min Act: -0.0000

Data Index: 949751 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.2029. Min Act: -0.0000

Data Index: 1973517 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.2013. Min Act: -0.0000

Data Index: 1398229 (The Pile)

Max Activating Token Index: 140

Text #3

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.1825. Min Act: -0.0000

Data Index: 209934 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1041931 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1771533 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1598958 (The Pile)

Max Activating Token Index: 830

Text #7

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0402. Min Act: -0.0000

Data Index: 320586 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0143. Min Act: -0.0000

Data Index: 1906979 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0333. Min Act: -0.0000

Data Index: 1109170 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1056888 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9403. Min Act: -0.0000

Data Index: 807847 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0290. Min Act: -0.0000

Data Index: 433491 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9780. Min Act: -0.0000

Data Index: 337058 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1391981 (The Pile)

Max Activating Token Index: 441

Text #15

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9131. Min Act: -0.0000

Data Index: 352150 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1247304 (The Pile)

Max Activating Token Index: 670

Text #17

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0175. Min Act: -0.0000

Data Index: 724688 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9880. Min Act: -0.0000

Data Index: 896912 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1438443 (The Pile)

Max Activating Token Index: 882