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

Dataset: The Pile

Neuron 697 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1689427 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2446. Min Act: -0.0000

Data Index: 37092 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2021. Min Act: -0.0000

Data Index: 669823 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1568696 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1555272 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1772. Min Act: -0.0000

Data Index: 357311 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1757. Min Act: -0.0000

Data Index: 23038 (The Pile)

Max Activating Token Index: 725

Text #7

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1772. Min Act: 0.0000

Data Index: 1521004 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1492. Min Act: 0.0000

Data Index: 828453 (The Pile)

Max Activating Token Index: 603

Text #9

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1728. Min Act: -0.0000

Data Index: 533040 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1344471 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1888103 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1541. Min Act: -0.0000

Data Index: 534902 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1531270 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1612. Min Act: -0.0000

Data Index: 301863 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1600. Min Act: -0.0000

Data Index: 386214 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1271702 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1553. Min Act: -0.0000

Data Index: 881987 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1692350 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1023922 (The Pile)

Max Activating Token Index: 704