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

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

Neuron 578 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1860. Min Act: -0.0001

Data Index: 405422 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1648. Min Act: -0.0001

Data Index: 436021 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1458. Min Act: -0.0001

Data Index: 813507 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1144156 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1430. Min Act: -0.0001

Data Index: 195193 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1514. Min Act: -0.0001

Data Index: 358503 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1153079 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1370. Min Act: -0.0001

Data Index: 198643 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1411. Min Act: -0.0001

Data Index: 348546 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1404. Min Act: -0.0001

Data Index: 666816 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1476. Min Act: -0.0001

Data Index: 235728 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1498. Min Act: -0.0001

Data Index: 129951 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1398. Min Act: -0.0001

Data Index: 789996 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1380. Min Act: -0.0001

Data Index: 574872 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1002084 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1114953 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1130269 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1008132 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1357. Min Act: -0.0001

Data Index: 351864 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1351. Min Act: -0.0001

Data Index: 656693 (C4 (Web Text))

Max Activating Token Index: 194