Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3837 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1506168 (Python Code)

Max Activating Token Index: 388

Text #1

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1719. Min Act: -0.0001

Data Index: 643247 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1717. Min Act: -0.0001

Data Index: 432746 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1701. Min Act: -0.0001

Data Index: 436008 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1690. Min Act: -0.0001

Data Index: 777595 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1555. Min Act: -0.0001

Data Index: 209731 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1219142 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1458. Min Act: -0.0001

Data Index: 410055 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1533. Min Act: -0.0001

Data Index: 355861 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1499. Min Act: -0.0001

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1193809 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1003173 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1525. Min Act: -0.0001

Data Index: 724423 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1364. Min Act: -0.0001

Data Index: 849929 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1418. Min Act: -0.0001

Data Index: 326146 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1462. Min Act: -0.0001

Data Index: 148845 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1357112 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1393. Min Act: -0.0001

Data Index: 74217 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1624753 (Python Code)

Max Activating Token Index: 101

Text #19

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1370. Min Act: -0.0001

Data Index: 562427 (C4 (Web Text))

Max Activating Token Index: 344