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

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

Neuron 1433 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1643. Min Act: -0.0002

Data Index: 319310 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1627. Min Act: -0.0002

Data Index: 1042121 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1612. Min Act: -0.0002

Data Index: 182784 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1607. Min Act: -0.0002

Data Index: 19895 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1469. Min Act: -0.0002

Data Index: 971981 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1412. Min Act: -0.0002

Data Index: 1240122 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1433. Min Act: -0.0002

Data Index: 1275971 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1583. Min Act: -0.0002

Data Index: 95566 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1194036 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1421. Min Act: -0.0002

Data Index: 1093270 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1427. Min Act: -0.0002

Data Index: 781836 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1433. Min Act: -0.0002

Data Index: 1116319 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1423. Min Act: -0.0002

Data Index: 1289668 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1402. Min Act: -0.0002

Data Index: 140521 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1309. Min Act: -0.0002

Data Index: 155945 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1338. Min Act: -0.0002

Data Index: 310550 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1322. Min Act: -0.0002

Data Index: 1169336 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1308. Min Act: -0.0002

Data Index: 396256 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1312. Min Act: -0.0002

Data Index: 656381 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1341. Min Act: -0.0002

Data Index: 432711 (C4 (Web Text))

Max Activating Token Index: 789