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

Dataset: The Pile

Neuron 4957 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: 3.6262. Min Range: -3.6262

Max Act: 3.6262. Min Act: -0.0000

Data Index: 1452819 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.3277. Min Act: -0.0000

Data Index: 1281065 (The Pile)

Max Activating Token Index: 896

Text #2

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.2336. Min Act: -0.0000

Data Index: 1087475 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.2197. Min Act: -0.0000

Data Index: 108427 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.3596. Min Act: -0.0000

Data Index: 450697 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.0114. Min Act: -0.0000

Data Index: 24471 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.3032. Min Act: -0.0000

Data Index: 551670 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.1455. Min Act: -0.0000

Data Index: 1895731 (The Pile)

Max Activating Token Index: 963

Text #8

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.1121. Min Act: -0.0000

Data Index: 1012565 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.1267. Min Act: -0.0000

Data Index: 40436 (The Pile)

Max Activating Token Index: 882

Text #10

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.0711. Min Act: -0.0000

Data Index: 1999635 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.0615. Min Act: -0.0000

Data Index: 1327349 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.0551. Min Act: -0.0000

Data Index: 1001192 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.0497. Min Act: -0.0000

Data Index: 1350798 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 3.6262. Min Range: -3.6262

Max Act: 2.8858. Min Act: -0.0000

Data Index: 1123592 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.0192. Min Act: -0.0000

Data Index: 282527 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.0159. Min Act: -0.0000

Data Index: 733719 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.1634. Min Act: -0.0000

Data Index: 669536 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 3.6262. Min Range: -3.6262

Max Act: 3.0186. Min Act: -0.0000

Data Index: 905431 (The Pile)

Max Activating Token Index: 96

Text #19

Max Range: 3.6262. Min Range: -3.6262

Max Act: 2.8529. Min Act: -0.0000

Data Index: 361707 (The Pile)

Max Activating Token Index: 207