Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 852 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1762. Min Act: -0.0001

Data Index: 339699 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1534. Min Act: -0.0001

Data Index: 375195 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1349478 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1530. Min Act: -0.0001

Data Index: 903916 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1649. Min Act: -0.0001

Data Index: 58668 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1483. Min Act: -0.0001

Data Index: 43973 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1525. Min Act: -0.0001

Data Index: 361829 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1419. Min Act: -0.0001

Data Index: 159296 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1283. Min Act: -0.0001

Data Index: 63450 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1343. Min Act: -0.0001

Data Index: 653042 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1287. Min Act: -0.0001

Data Index: 383673 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1326. Min Act: -0.0001

Data Index: 683913 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1515. Min Act: -0.0001

Data Index: 848342 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1366. Min Act: -0.0001

Data Index: 941305 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1142842 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1308. Min Act: -0.0001

Data Index: 255840 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1220502 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1392. Min Act: -0.0001

Data Index: 969773 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1340658 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1349. Min Act: -0.0001

Data Index: 987549 (C4 (Web Text))

Max Activating Token Index: 1001