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

Dataset: The Pile

Neuron 1943 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: 1.3832. Min Range: -1.3832

Max Act: 1.3832. Min Act: -0.0000

Data Index: 1654080 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1397003 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1765628 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.1609. Min Act: -0.0000

Data Index: 1883475 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.2811. Min Act: -0.0000

Data Index: 1848715 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.1074. Min Act: -0.0000

Data Index: 1418741 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0744. Min Act: -0.0000

Data Index: 435511 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0469. Min Act: -0.0000

Data Index: 597636 (The Pile)

Max Activating Token Index: 395

Text #8

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.9866. Min Act: -0.0000

Data Index: 191626 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0192. Min Act: -0.0000

Data Index: 274690 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.8426. Min Act: -0.0000

Data Index: 650326 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.9620. Min Act: -0.0000

Data Index: 418705 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1985993 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.9365. Min Act: -0.0000

Data Index: 323306 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.9288. Min Act: -0.0000

Data Index: 558708 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1341893 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.8793. Min Act: -0.0000

Data Index: 14065 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1266267 (The Pile)

Max Activating Token Index: 508

Text #18

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1478629 (The Pile)

Max Activating Token Index: 266

Text #19

Max Range: 1.3832. Min Range: -1.3832

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1547429 (The Pile)

Max Activating Token Index: 487