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

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

Neuron 1471 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1949. Min Act: -0.0000

Data Index: 113306 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1421940 (Python Code)

Max Activating Token Index: 665

Text #2

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1816. Min Act: -0.0000

Data Index: 446428 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1289322 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1771. Min Act: -0.0000

Data Index: 106457 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1751. Min Act: -0.0000

Data Index: 146798 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1702. Min Act: -0.0000

Data Index: 706443 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1038311 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1789. Min Act: -0.0000

Data Index: 507116 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1607. Min Act: -0.0000

Data Index: 772993 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1661. Min Act: -0.0000

Data Index: 521287 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1591. Min Act: -0.0000

Data Index: 832762 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1593. Min Act: -0.0000

Data Index: 120388 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1668. Min Act: -0.0000

Data Index: 540992 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1576. Min Act: -0.0000

Data Index: 456017 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1075764 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1346620 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1591. Min Act: -0.0000

Data Index: 54118 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1585. Min Act: -0.0000

Data Index: 631209 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1480. Min Act: -0.0000

Data Index: 654090 (C4 (Web Text))

Max Activating Token Index: 694