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

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

Neuron 2246 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: 0.1809. Min Range: -0.1809

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1265089 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1761. Min Act: -0.0001

Data Index: 71948 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1780. Min Act: -0.0001

Data Index: 738561 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1650. Min Act: -0.0001

Data Index: 668538 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1648. Min Act: -0.0001

Data Index: 524240 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1516. Min Act: -0.0001

Data Index: 212437 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1624. Min Act: -0.0001

Data Index: 1337521 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1202041 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1031072 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1286790 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1342. Min Act: -0.0001

Data Index: 98917 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1478. Min Act: -0.0001

Data Index: 767484 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1188477 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1457. Min Act: -0.0001

Data Index: 516820 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1410. Min Act: -0.0001

Data Index: 323960 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1403. Min Act: -0.0001

Data Index: 235339 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1394. Min Act: -0.0001

Data Index: 1331850 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1464. Min Act: -0.0001

Data Index: 454731 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1422. Min Act: -0.0001

Data Index: 500285 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1001138 (C4 (Web Text))

Max Activating Token Index: 933