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

Dataset: The Pile

Neuron 749 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.3383. Min Act: -0.0000

Data Index: 301039 (The Pile)

Max Activating Token Index: 106

Text #1

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.4635. Min Act: -0.0000

Data Index: 1765523 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1992. Min Act: -0.0000

Data Index: 3425 (The Pile)

Max Activating Token Index: 892

Text #3

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1707675 (The Pile)

Max Activating Token Index: 574

Text #4

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1547610 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0333. Min Act: -0.0000

Data Index: 492175 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0837. Min Act: -0.0000

Data Index: 632684 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1124203 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9995. Min Act: -0.0000

Data Index: 961969 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1524700 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1164987 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0092. Min Act: -0.0000

Data Index: 204199 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9577. Min Act: -0.0000

Data Index: 524319 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0232. Min Act: -0.0000

Data Index: 423805 (The Pile)

Max Activating Token Index: 927

Text #14

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1504989 (The Pile)

Max Activating Token Index: 429

Text #15

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1640372 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.7878. Min Act: -0.0000

Data Index: 900286 (The Pile)

Max Activating Token Index: 434

Text #17

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.9613. Min Act: -0.0000

Data Index: 918700 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 1.4635. Min Range: -1.4635

Max Act: 0.8378. Min Act: -0.0000

Data Index: 804531 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1873055 (The Pile)

Max Activating Token Index: 5