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

Dataset: The Pile

Neuron 4802 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1526112 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.1544. Min Act: -0.0000

Data Index: 743476 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1781900 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.1200. Min Act: -0.0000

Data Index: 1396555 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1995686 (The Pile)

Max Activating Token Index: 444

Text #5

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.1523. Min Act: -0.0000

Data Index: 103437 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1234893 (The Pile)

Max Activating Token Index: 626

Text #7

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1385921 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.0019. Min Act: -0.0000

Data Index: 301638 (The Pile)

Max Activating Token Index: 525

Text #9

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1346156 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1661117 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1071915 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8897. Min Act: -0.0000

Data Index: 464939 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9148. Min Act: -0.0000

Data Index: 552931 (The Pile)

Max Activating Token Index: 813

Text #14

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1659877 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8562. Min Act: -0.0000

Data Index: 314618 (The Pile)

Max Activating Token Index: 692

Text #16

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1435416 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8360. Min Act: 0.0000

Data Index: 494288 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1288153 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8655. Min Act: -0.0000

Data Index: 679809 (The Pile)

Max Activating Token Index: 367