Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 76 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1747. Min Act: -0.0006

Data Index: 401063 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1805. Min Act: -0.0006

Data Index: 967152 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1616. Min Act: -0.0006

Data Index: 69690 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1682. Min Act: -0.0006

Data Index: 896454 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1537. Min Act: -0.0006

Data Index: 593723 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1525. Min Act: -0.0006

Data Index: 314774 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1578. Min Act: -0.0006

Data Index: 560504 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1568. Min Act: -0.0006

Data Index: 413727 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1504. Min Act: -0.0006

Data Index: 365007 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1440. Min Act: -0.0006

Data Index: 400643 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1278. Min Act: -0.0006

Data Index: 718924 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1488. Min Act: -0.0006

Data Index: 475764 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1578. Min Act: -0.0006

Data Index: 416481 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1633. Min Act: -0.0006

Data Index: 1128425 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1508. Min Act: -0.0006

Data Index: 851506 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1497. Min Act: -0.0006

Data Index: 247208 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1499. Min Act: -0.0006

Data Index: 231689 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1379. Min Act: -0.0006

Data Index: 35622 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1423. Min Act: -0.0006

Data Index: 1114818 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1519. Min Act: -0.0006

Data Index: 942478 (C4 (Web Text))

Max Activating Token Index: 537