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

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

Neuron 3813 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.3167. Min Act: -0.0000

Data Index: 1076537 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1187293 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.2799. Min Act: -0.0000

Data Index: 407021 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.1690. Min Act: -0.0000

Data Index: 10696 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1386053 (Python Code)

Max Activating Token Index: 103

Text #5

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.1991. Min Act: -0.0000

Data Index: 243966 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.1115. Min Act: -0.0000

Data Index: 687209 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1013965 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1101564 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0254. Min Act: -0.0000

Data Index: 284662 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.1785. Min Act: -0.0000

Data Index: 763062 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0694. Min Act: -0.0000

Data Index: 180159 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9986. Min Act: -0.0000

Data Index: 1403721 (Python Code)

Max Activating Token Index: 215

Text #13

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1009049 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0506. Min Act: -0.0000

Data Index: 421450 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.1710. Min Act: -0.0000

Data Index: 777275 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1254834 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1385108 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0206. Min Act: -0.0000

Data Index: 8046 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1577276 (Python Code)

Max Activating Token Index: 965