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

Dataset: The Pile

Neuron 1922 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: 0.9483. Min Range: -0.9483

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1307076 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1940403 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7605. Min Act: -0.0000

Data Index: 158350 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7435. Min Act: -0.0000

Data Index: 851088 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6725. Min Act: -0.0000

Data Index: 569375 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1100203 (The Pile)

Max Activating Token Index: 9

Text #6

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1175058 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1300360 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1131967 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1497467 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1937962 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7335. Min Act: -0.0000

Data Index: 318966 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1914883 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1984411 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1369400 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6894. Min Act: -0.0000

Data Index: 964549 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1299327 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1064244 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1801921 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6780. Min Act: -0.0000

Data Index: 690861 (The Pile)

Max Activating Token Index: 33