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

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

Neuron 586 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: 0.5526. Min Range: -0.5526

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1430088 (Python Code)

Max Activating Token Index: 984

Text #1

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1461902 (Python Code)

Max Activating Token Index: 654

Text #2

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1445147 (Python Code)

Max Activating Token Index: 948

Text #3

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2661. Min Act: -0.0000

Data Index: 720627 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2530. Min Act: -0.0000

Data Index: 446325 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1281616 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1471617 (Python Code)

Max Activating Token Index: 406

Text #7

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2635. Min Act: -0.0000

Data Index: 395664 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1415752 (Python Code)

Max Activating Token Index: 961

Text #9

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2429. Min Act: -0.0000

Data Index: 132220 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1087357 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1593700 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2177. Min Act: -0.0000

Data Index: 22927 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.1943. Min Act: -0.0000

Data Index: 864120 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2082. Min Act: -0.0000

Data Index: 985326 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1539755 (Python Code)

Max Activating Token Index: 704

Text #16

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1095101 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2015. Min Act: -0.0000

Data Index: 385095 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2229. Min Act: -0.0000

Data Index: 715907 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.2116. Min Act: -0.0000

Data Index: 648481 (C4 (Web Text))

Max Activating Token Index: 980