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

Dataset: The Pile

Neuron 274 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0865. Min Range: -1.0865

Max Act: 1.0865. Min Act: -0.0000

Data Index: 920155 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 1.0865. Min Range: -1.0865

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1017295 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 1.0865. Min Range: -1.0865

Max Act: 1.0093. Min Act: -0.0000

Data Index: 164382 (The Pile)

Max Activating Token Index: 744

Text #3

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.9373. Min Act: -0.0000

Data Index: 917214 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.8536. Min Act: -0.0000

Data Index: 832456 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1200907 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7790. Min Act: -0.0000

Data Index: 448596 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1592284 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.8193. Min Act: -0.0000

Data Index: 451025 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1434688 (The Pile)

Max Activating Token Index: 427

Text #10

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7275. Min Act: -0.0000

Data Index: 961699 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7911. Min Act: -0.0000

Data Index: 652643 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.5974. Min Act: -0.0000

Data Index: 91834 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1292441 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7159. Min Act: -0.0000

Data Index: 198110 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1566892 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1662109 (The Pile)

Max Activating Token Index: 983

Text #17

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1389188 (The Pile)

Max Activating Token Index: 54

Text #18

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1750188 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1182787 (The Pile)

Max Activating Token Index: 489