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

Dataset: The Pile

Neuron 3555 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: 1.6527. Min Range: -1.6527

Max Act: 1.6527. Min Act: -0.0000

Data Index: 1760814 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.4836. Min Act: -0.0000

Data Index: 1137838 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1084702 (The Pile)

Max Activating Token Index: 5

Text #3

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1395131 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2789. Min Act: -0.0000

Data Index: 1853364 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2284. Min Act: -0.0000

Data Index: 1406602 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1767166 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1361986 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 1.6527. Min Range: -1.6527

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1897017 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1349606 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1853846 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1929614 (The Pile)

Max Activating Token Index: 132

Text #12

Max Range: 1.6527. Min Range: -1.6527

Max Act: 0.9790. Min Act: -0.0000

Data Index: 665725 (The Pile)

Max Activating Token Index: 510

Text #13

Max Range: 1.6527. Min Range: -1.6527

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1457143 (The Pile)

Max Activating Token Index: 3

Text #14

Max Range: 1.6527. Min Range: -1.6527

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1545184 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 1.6527. Min Range: -1.6527

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1324528 (The Pile)

Max Activating Token Index: 519

Text #16

Max Range: 1.6527. Min Range: -1.6527

Max Act: 0.7881. Min Act: -0.0000

Data Index: 77347 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 1.6527. Min Range: -1.6527

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1993032 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 1.6527. Min Range: -1.6527

Max Act: 0.8933. Min Act: -0.0000

Data Index: 864327 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 1.6527. Min Range: -1.6527

Max Act: 0.8646. Min Act: -0.0000

Data Index: 212315 (The Pile)

Max Activating Token Index: 582