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

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

Neuron 1745 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: 0.1787. Min Range: -0.1787

Max Act: 0.1628. Min Act: -0.0001

Data Index: 945386 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1495. Min Act: -0.0001

Data Index: 848418 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1166967 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1260. Min Act: -0.0001

Data Index: 348716 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1550. Min Act: -0.0001

Data Index: 293662 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1600. Min Act: -0.0001

Data Index: 334525 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1787. Min Act: -0.0001

Data Index: 381489 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1172916 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1720. Min Act: -0.0001

Data Index: 408533 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1450. Min Act: -0.0001

Data Index: 964684 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1200748 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1511. Min Act: -0.0001

Data Index: 973267 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1504. Min Act: -0.0001

Data Index: 554833 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1168667 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1102654 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1331. Min Act: -0.0001

Data Index: 1273203 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1478. Min Act: -0.0002

Data Index: 1235716 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1093702 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1000032 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1068171 (C4 (Web Text))

Max Activating Token Index: 280