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

Dataset: The Pile

Neuron 1423 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: 1.4670. Min Range: -1.4670

Max Act: 1.4670. Min Act: -0.0000

Data Index: 1714317 (The Pile)

Max Activating Token Index: 401

Text #1

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.1739. Min Act: -0.0000

Data Index: 1540178 (The Pile)

Max Activating Token Index: 244

Text #2

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1453887 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1244098 (The Pile)

Max Activating Token Index: 943

Text #4

Max Range: 1.4670. Min Range: -1.4670

Max Act: 1.0199. Min Act: -0.0000

Data Index: 600922 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1037852 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9501. Min Act: -0.0000

Data Index: 714292 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1811004 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9403. Min Act: -0.0000

Data Index: 555329 (The Pile)

Max Activating Token Index: 748

Text #9

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9349. Min Act: -0.0000

Data Index: 548813 (The Pile)

Max Activating Token Index: 68

Text #10

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8668. Min Act: -0.0000

Data Index: 97728 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1348255 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9019. Min Act: -0.0000

Data Index: 516174 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1637409 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8082. Min Act: -0.0000

Data Index: 935492 (The Pile)

Max Activating Token Index: 36

Text #15

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1845268 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8341. Min Act: -0.0000

Data Index: 4730 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.9091. Min Act: -0.0000

Data Index: 408767 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1722241 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 1.4670. Min Range: -1.4670

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1644353 (The Pile)

Max Activating Token Index: 36