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

Dataset: The Pile

Neuron 4780 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: 1.6391. Min Range: -1.6391

Max Act: 1.6391. Min Act: -0.0000

Data Index: 89918 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.4728. Min Act: -0.0000

Data Index: 1351253 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1623661 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.3060. Min Act: -0.0000

Data Index: 457031 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.3058. Min Act: -0.0000

Data Index: 563127 (The Pile)

Max Activating Token Index: 340

Text #5

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.2304. Min Act: -0.0000

Data Index: 299865 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.1883. Min Act: -0.0000

Data Index: 570007 (The Pile)

Max Activating Token Index: 629

Text #7

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.1872. Min Act: -0.0000

Data Index: 912557 (The Pile)

Max Activating Token Index: 493

Text #8

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.1088. Min Act: -0.0000

Data Index: 501182 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1598195 (The Pile)

Max Activating Token Index: 504

Text #10

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1939422 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.1242. Min Act: -0.0000

Data Index: 775600 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1708726 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.0996. Min Act: -0.0000

Data Index: 1158176 (The Pile)

Max Activating Token Index: 202

Text #14

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.1003. Min Act: -0.0000

Data Index: 882140 (The Pile)

Max Activating Token Index: 590

Text #15

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1784830 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1251445 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.1220. Min Act: -0.0000

Data Index: 388369 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1086560 (The Pile)

Max Activating Token Index: 548

Text #19

Max Range: 1.6391. Min Range: -1.6391

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1212515 (The Pile)

Max Activating Token Index: 434