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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2596 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.3116. Min Act: -0.0000

Data Index: 843115 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1026635 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2170. Min Act: -0.0000

Data Index: 134668 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1125573 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2071. Min Act: -0.0000

Data Index: 994383 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1272597 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1332925 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1948. Min Act: -0.0000

Data Index: 144152 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1131126 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1861. Min Act: -0.0000

Data Index: 949151 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1340958 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1929. Min Act: -0.0000

Data Index: 462929 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1210811 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1761. Min Act: -0.0000

Data Index: 343778 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1919. Min Act: -0.0000

Data Index: 218749 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1671. Min Act: -0.0000

Data Index: 984921 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1739. Min Act: -0.0000

Data Index: 66504 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1493. Min Act: -0.0000

Data Index: 823933 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1714. Min Act: -0.0000

Data Index: 802180 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1168014 (C4 (Web Text))

Max Activating Token Index: 431