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

Dataset: The Pile

Neuron 2271 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: 1.5840. Min Range: -1.5840

Max Act: 1.5352. Min Act: -0.0000

Data Index: 1735109 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.5840. Min Act: -0.0000

Data Index: 987665 (The Pile)

Max Activating Token Index: 669

Text #2

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2142. Min Act: -0.0000

Data Index: 162822 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.1194. Min Act: -0.0000

Data Index: 25310 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0965. Min Act: -0.0000

Data Index: 657231 (The Pile)

Max Activating Token Index: 634

Text #5

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2136. Min Act: -0.0000

Data Index: 1752129 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0470. Min Act: -0.0000

Data Index: 51035 (The Pile)

Max Activating Token Index: 660

Text #7

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1584984 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0973. Min Act: -0.0000

Data Index: 831130 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 1.5840. Min Range: -1.5840

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1011260 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.1085. Min Act: -0.0000

Data Index: 1176324 (The Pile)

Max Activating Token Index: 129

Text #11

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0627. Min Act: -0.0000

Data Index: 521553 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0306. Min Act: -0.0000

Data Index: 618818 (The Pile)

Max Activating Token Index: 359

Text #13

Max Range: 1.5840. Min Range: -1.5840

Max Act: 0.9922. Min Act: -0.0000

Data Index: 803513 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1983803 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.1336. Min Act: -0.0000

Data Index: 160883 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0227. Min Act: -0.0000

Data Index: 239717 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 1.5840. Min Range: -1.5840

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1753649 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 1.5840. Min Range: -1.5840

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1534171 (The Pile)

Max Activating Token Index: 38

Text #19

Max Range: 1.5840. Min Range: -1.5840

Max Act: 0.9683. Min Act: -0.0000

Data Index: 124803 (The Pile)

Max Activating Token Index: 665