Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 225 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.2088. Min Act: -0.0000

Data Index: 931610 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.2060. Min Act: -0.0000

Data Index: 178279 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1658. Min Act: -0.0000

Data Index: 951681 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1867. Min Act: -0.0000

Data Index: 144414 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1645. Min Act: -0.0000

Data Index: 661242 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1589. Min Act: -0.0000

Data Index: 63374 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1358272 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1533. Min Act: -0.0000

Data Index: 994822 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1592. Min Act: -0.0000

Data Index: 756654 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1458. Min Act: -0.0000

Data Index: 397723 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1472. Min Act: -0.0000

Data Index: 655487 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1700. Min Act: -0.0000

Data Index: 315263 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1096942 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1468. Min Act: -0.0000

Data Index: 800473 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1065820 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1631. Min Act: -0.0000

Data Index: 760863 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1443. Min Act: -0.0000

Data Index: 747453 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1706. Min Act: -0.0000

Data Index: 119574 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1058906 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1532. Min Act: -0.0000

Data Index: 395830 (C4 (Web Text))

Max Activating Token Index: 441