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

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

Neuron 43 in Layer 4

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: 0.1787. Min Act: -0.0001

Data Index: 257055 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1741. Min Act: -0.0001

Data Index: 1184524 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1447243 (Python Code)

Max Activating Token Index: 491

Text #3

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1757. Min Act: -0.0001

Data Index: 618585 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1471. Min Act: -0.0001

Data Index: 612708 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1504. Min Act: -0.0001

Data Index: 538005 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1612. Min Act: -0.0001

Data Index: 209872 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1609. Min Act: -0.0001

Data Index: 375519 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1503. Min Act: -0.0001

Data Index: 130032 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1398. Min Act: -0.0001

Data Index: 639524 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1441. Min Act: -0.0001

Data Index: 466745 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1548. Min Act: -0.0001

Data Index: 855233 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1329796 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1009582 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1470. Min Act: -0.0001

Data Index: 481371 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1066951 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1496. Min Act: -0.0001

Data Index: 377327 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1124402 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1604. Min Act: -0.0001

Data Index: 580775 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1355. Min Act: -0.0001

Data Index: 589614 (C4 (Web Text))

Max Activating Token Index: 646