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

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

Neuron 3033 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: 1.7914. Min Range: -1.7914

Max Act: 1.7914. Min Act: -0.0000

Data Index: 266257 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.7725. Min Act: -0.0000

Data Index: 22887 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.7577. Min Act: -0.0000

Data Index: 416841 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.7278. Min Act: -0.0000

Data Index: 126062 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6299. Min Act: -0.0000

Data Index: 919551 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6924. Min Act: -0.0000

Data Index: 857915 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6603. Min Act: -0.0000

Data Index: 1104943 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6318. Min Act: -0.0000

Data Index: 84937 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5293. Min Act: -0.0000

Data Index: 341848 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5759. Min Act: -0.0000

Data Index: 537507 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5570. Min Act: -0.0000

Data Index: 877115 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5470. Min Act: -0.0000

Data Index: 453365 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4658. Min Act: -0.0000

Data Index: 1347855 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5242. Min Act: -0.0000

Data Index: 308173 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4854. Min Act: -0.0000

Data Index: 1143501 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.3959. Min Act: -0.0000

Data Index: 625783 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4662. Min Act: -0.0000

Data Index: 514592 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1170553 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4483. Min Act: -0.0000

Data Index: 986813 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4484. Min Act: -0.0000

Data Index: 6369 (C4 (Web Text))

Max Activating Token Index: 884