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

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

Neuron 2604 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: 0.1983. Min Range: -0.1983

Max Act: 0.1983. Min Act: -0.0001

Data Index: 805495 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1671. Min Act: -0.0001

Data Index: 233349 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1739. Min Act: -0.0001

Data Index: 568830 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1579. Min Act: -0.0001

Data Index: 660040 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1583. Min Act: -0.0001

Data Index: 128648 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1626. Min Act: -0.0001

Data Index: 1329796 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1575. Min Act: -0.0001

Data Index: 994208 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1563. Min Act: -0.0001

Data Index: 120273 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1516. Min Act: -0.0001

Data Index: 350209 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1501. Min Act: -0.0001

Data Index: 838554 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1310944 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1333373 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1562. Min Act: -0.0001

Data Index: 676860 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1503. Min Act: -0.0001

Data Index: 219727 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1438. Min Act: -0.0001

Data Index: 482586 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1559. Min Act: -0.0001

Data Index: 529409 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1427. Min Act: -0.0001

Data Index: 580496 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1572. Min Act: -0.0001

Data Index: 966878 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1527. Min Act: -0.0001

Data Index: 195780 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1369. Min Act: -0.0001

Data Index: 496944 (C4 (Web Text))

Max Activating Token Index: 980