Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2654 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1744. Min Act: -0.0001

Data Index: 173375 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1545. Min Act: -0.0001

Data Index: 486731 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1585. Min Act: -0.0001

Data Index: 500216 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1567. Min Act: -0.0001

Data Index: 624980 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1469. Min Act: -0.0001

Data Index: 766101 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1570. Min Act: -0.0001

Data Index: 34391 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1231. Min Act: -0.0001

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1437. Min Act: -0.0001

Data Index: 265596 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1547. Min Act: -0.0001

Data Index: 994115 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1032254 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1366. Min Act: -0.0001

Data Index: 871408 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1475. Min Act: -0.0001

Data Index: 62524 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1396. Min Act: -0.0001

Data Index: 787956 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1318452 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1574. Min Act: -0.0001

Data Index: 1302040 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1347. Min Act: -0.0001

Data Index: 651182 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1007719 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1615. Min Act: -0.0001

Data Index: 1083801 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1492. Min Act: -0.0001

Data Index: 196487 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1237. Min Act: -0.0001

Data Index: 167624 (C4 (Web Text))

Max Activating Token Index: 536