Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1265374 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1396888 (Python Code)

Max Activating Token Index: 275

Text #2

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1788. Min Act: -0.0000

Data Index: 720500 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1333413 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1682. Min Act: -0.0000

Data Index: 1466595 (Python Code)

Max Activating Token Index: 837

Text #5

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1496552 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1588. Min Act: -0.0000

Data Index: 741578 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1544. Min Act: -0.0000

Data Index: 402747 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1683. Min Act: -0.0000

Data Index: 612052 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1422. Min Act: -0.0000

Data Index: 279288 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1339. Min Act: -0.0000

Data Index: 92021 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1405. Min Act: -0.0000

Data Index: 536905 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1422966 (Python Code)

Max Activating Token Index: 333

Text #13

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1398027 (Python Code)

Max Activating Token Index: 796

Text #14

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1636492 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1360951 (Python Code)

Max Activating Token Index: 1004

Text #16

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1464683 (Python Code)

Max Activating Token Index: 401

Text #17

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1552384 (Python Code)

Max Activating Token Index: 965

Text #18

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1288. Min Act: -0.0000

Data Index: 7081 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1642735 (Python Code)

Max Activating Token Index: 111