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

Dataset: The Pile

Neuron 1618 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: 3.6832. Min Range: -3.6832

Max Act: 3.3677. Min Act: -0.0000

Data Index: 350892 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 3.6832. Min Range: -3.6832

Max Act: 3.2493. Min Act: -0.0000

Data Index: 1695620 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 3.6832. Min Range: -3.6832

Max Act: 3.0389. Min Act: -0.0000

Data Index: 483330 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 3.6832. Min Range: -3.6832

Max Act: 3.6832. Min Act: -0.0000

Data Index: 1004544 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.6686. Min Act: -0.0000

Data Index: 761760 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.7745. Min Act: -0.0000

Data Index: 375372 (The Pile)

Max Activating Token Index: 494

Text #6

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.9301. Min Act: -0.0000

Data Index: 1976410 (The Pile)

Max Activating Token Index: 256

Text #7

Max Range: 3.6832. Min Range: -3.6832

Max Act: 3.0491. Min Act: -0.0000

Data Index: 1103838 (The Pile)

Max Activating Token Index: 400

Text #8

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.9648. Min Act: -0.0000

Data Index: 608958 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.5611. Min Act: -0.0000

Data Index: 815081 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.7725. Min Act: -0.0000

Data Index: 554659 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 3.6832. Min Range: -3.6832

Max Act: 3.2291. Min Act: -0.0000

Data Index: 1640015 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.7966. Min Act: -0.0000

Data Index: 68503 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.7555. Min Act: -0.0000

Data Index: 366692 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.6406. Min Act: -0.0000

Data Index: 824212 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.9353. Min Act: -0.0000

Data Index: 1512265 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.6713. Min Act: -0.0000

Data Index: 90707 (The Pile)

Max Activating Token Index: 333

Text #17

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.7907. Min Act: -0.0000

Data Index: 1247164 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.6683. Min Act: -0.0000

Data Index: 591043 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 3.6832. Min Range: -3.6832

Max Act: 2.6703. Min Act: -0.0000

Data Index: 685702 (The Pile)

Max Activating Token Index: 313