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

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

Neuron 1334 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.2131. Min Act: -0.0001

Data Index: 1212630 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1991. Min Act: -0.0000

Data Index: 709332 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1813. Min Act: -0.0000

Data Index: 195245 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1749. Min Act: -0.0000

Data Index: 334973 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1195360 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1164129 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1707. Min Act: -0.0000

Data Index: 877715 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1292384 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1640. Min Act: -0.0000

Data Index: 134991 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1625. Min Act: -0.0000

Data Index: 642316 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1230487 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1701. Min Act: -0.0000

Data Index: 324805 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1077129 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1605. Min Act: -0.0000

Data Index: 985638 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1659. Min Act: -0.0000

Data Index: 824514 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1189547 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1256376 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1562. Min Act: -0.0000

Data Index: 749952 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1553. Min Act: -0.0000

Data Index: 377938 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1590. Min Act: -0.0000

Data Index: 266154 (C4 (Web Text))

Max Activating Token Index: 114