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

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

Neuron 3262 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: 0.2543. Min Range: -0.2543

Max Act: 0.2543. Min Act: -0.0001

Data Index: 1065897 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1738. Min Act: -0.0000

Data Index: 997594 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1789. Min Act: -0.0000

Data Index: 809005 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1671. Min Act: -0.0000

Data Index: 745456 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1694. Min Act: -0.0001

Data Index: 627740 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1630. Min Act: -0.0000

Data Index: 38817 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1202996 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1657. Min Act: -0.0001

Data Index: 950665 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1752. Min Act: -0.0001

Data Index: 605037 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1080833 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1691. Min Act: -0.0001

Data Index: 581226 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1332937 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1631. Min Act: -0.0000

Data Index: 811002 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1623. Min Act: -0.0001

Data Index: 522516 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1593. Min Act: -0.0000

Data Index: 705423 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1589. Min Act: -0.0000

Data Index: 893383 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1188088 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1645. Min Act: -0.0000

Data Index: 344537 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1607. Min Act: -0.0000

Data Index: 782749 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1576. Min Act: -0.0001

Data Index: 271470 (C4 (Web Text))

Max Activating Token Index: 66