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

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

Neuron 1587 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1723. Min Act: -0.0005

Data Index: 893928 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1687. Min Act: -0.0005

Data Index: 522552 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1666. Min Act: -0.0005

Data Index: 544283 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1624. Min Act: -0.0005

Data Index: 153499 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1690. Min Act: -0.0004

Data Index: 947483 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1616. Min Act: -0.0005

Data Index: 1152510 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1603. Min Act: -0.0005

Data Index: 1013720 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1583. Min Act: -0.0005

Data Index: 234289 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1538. Min Act: -0.0005

Data Index: 1174220 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1575. Min Act: -0.0005

Data Index: 991026 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1634. Min Act: -0.0005

Data Index: 619694 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1558. Min Act: -0.0005

Data Index: 436662 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1564. Min Act: -0.0005

Data Index: 24055 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1514. Min Act: -0.0005

Data Index: 811543 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1509. Min Act: -0.0005

Data Index: 862718 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1452. Min Act: -0.0004

Data Index: 436950 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1437. Min Act: -0.0005

Data Index: 829975 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1550. Min Act: -0.0005

Data Index: 410469 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1498. Min Act: -0.0005

Data Index: 547623 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1472. Min Act: -0.0005

Data Index: 385146 (C4 (Web Text))

Max Activating Token Index: 311