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

Dataset: The Pile

Neuron 2502 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: 0.2191. Min Range: -0.2191

Max Act: 0.2191. Min Act: -0.0000

Data Index: 95401 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1496821 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1482946 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.2033. Min Act: -0.0000

Data Index: 184279 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1838. Min Act: -0.0000

Data Index: 106732 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1537818 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1802. Min Act: -0.0000

Data Index: 447213 (The Pile)

Max Activating Token Index: 787

Text #7

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1262290 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1699. Min Act: -0.0000

Data Index: 713917 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1186209 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1524101 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1583. Min Act: -0.0000

Data Index: 583757 (The Pile)

Max Activating Token Index: 98

Text #12

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1517. Min Act: -0.0000

Data Index: 568214 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1289185 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1318546 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1093762 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1998328 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1649826 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1519305 (The Pile)

Max Activating Token Index: 910

Text #19

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1564. Min Act: -0.0000

Data Index: 976932 (The Pile)

Max Activating Token Index: 890