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

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

Neuron 3014 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1916. Min Act: -0.0001

Data Index: 925525 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1863. Min Act: -0.0001

Data Index: 707358 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1641. Min Act: -0.0001

Data Index: 652320 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1655. Min Act: -0.0001

Data Index: 75603 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1576. Min Act: -0.0001

Data Index: 778769 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1634. Min Act: -0.0001

Data Index: 1151726 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1653. Min Act: -0.0001

Data Index: 984701 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1534. Min Act: -0.0001

Data Index: 616933 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1638. Min Act: -0.0001

Data Index: 594792 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1549. Min Act: -0.0001

Data Index: 746506 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1508. Min Act: -0.0001

Data Index: 485559 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1526. Min Act: -0.0001

Data Index: 442553 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1498. Min Act: -0.0001

Data Index: 157755 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1446. Min Act: -0.0001

Data Index: 733580 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1495. Min Act: -0.0001

Data Index: 191582 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1431. Min Act: -0.0001

Data Index: 533703 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1479. Min Act: -0.0001

Data Index: 388868 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1108785 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1235783 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1452. Min Act: -0.0001

Data Index: 562743 (C4 (Web Text))

Max Activating Token Index: 11