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

Dataset: The Pile

Neuron 1365 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: 0.7553. Min Range: -0.7553

Max Act: 0.7553. Min Act: -0.0000

Data Index: 332942 (The Pile)

Max Activating Token Index: 602

Text #1

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1557743 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6498. Min Act: -0.0000

Data Index: 862024 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6465. Min Act: -0.0000

Data Index: 458470 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1483244 (The Pile)

Max Activating Token Index: 888

Text #5

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6477. Min Act: -0.0000

Data Index: 515370 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1556608 (The Pile)

Max Activating Token Index: 199

Text #7

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6174. Min Act: -0.0000

Data Index: 180866 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5939. Min Act: -0.0000

Data Index: 567797 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1467575 (The Pile)

Max Activating Token Index: 197

Text #10

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5947. Min Act: -0.0000

Data Index: 510008 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6065. Min Act: -0.0000

Data Index: 529823 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1010403 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5426. Min Act: -0.0000

Data Index: 680637 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1618819 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6023. Min Act: -0.0000

Data Index: 814024 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1660607 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6093. Min Act: -0.0000

Data Index: 690840 (The Pile)

Max Activating Token Index: 585

Text #18

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1901872 (The Pile)

Max Activating Token Index: 140

Text #19

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1377332 (The Pile)

Max Activating Token Index: 766