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

Dataset: The Pile

Neuron 3071 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.7317. Min Act: -0.0000

Data Index: 320539 (The Pile)

Max Activating Token Index: 216

Text #1

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6939. Min Act: -0.0000

Data Index: 845400 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6592. Min Act: -0.0000

Data Index: 727270 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1715404 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1231853 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6305. Min Act: -0.0000

Data Index: 175926 (The Pile)

Max Activating Token Index: 368

Text #6

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6159. Min Act: -0.0000

Data Index: 636547 (The Pile)

Max Activating Token Index: 608

Text #7

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1315556 (The Pile)

Max Activating Token Index: 184

Text #8

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6081. Min Act: -0.0000

Data Index: 889934 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5944. Min Act: -0.0000

Data Index: 528971 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6363. Min Act: -0.0000

Data Index: 178940 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1546993 (The Pile)

Max Activating Token Index: 840

Text #12

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5733. Min Act: 0.0000

Data Index: 1448921 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1696072 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1999824 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1852207 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1078837 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6310. Min Act: -0.0000

Data Index: 65762 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5642. Min Act: -0.0000

Data Index: 749670 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5854. Min Act: -0.0000

Data Index: 304371 (The Pile)

Max Activating Token Index: 743