Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 139 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2340. Min Act: -0.0001

Data Index: 160991 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2187. Min Act: -0.0001

Data Index: 1223880 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1855. Min Act: -0.0001

Data Index: 279257 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2016. Min Act: -0.0001

Data Index: 350224 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1909. Min Act: -0.0001

Data Index: 401758 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1905. Min Act: -0.0001

Data Index: 816807 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2029. Min Act: -0.0001

Data Index: 580369 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1831. Min Act: -0.0001

Data Index: 1324479 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1881. Min Act: -0.0001

Data Index: 188963 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1927. Min Act: -0.0001

Data Index: 750934 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1184645 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1782. Min Act: -0.0001

Data Index: 24209 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1232519 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1846. Min Act: -0.0001

Data Index: 1203827 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1900. Min Act: -0.0001

Data Index: 279973 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1777. Min Act: -0.0001

Data Index: 827762 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1828. Min Act: -0.0001

Data Index: 341244 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1286362 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1931. Min Act: -0.0001

Data Index: 438289 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1689. Min Act: -0.0001

Data Index: 921265 (C4 (Web Text))

Max Activating Token Index: 301