Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 38 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.6720. Min Act: -0.0000

Data Index: 795652 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.6364. Min Act: -0.0000

Data Index: 333568 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1654928 (The Pile)

Max Activating Token Index: 274

Text #3

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5299. Min Act: -0.0000

Data Index: 187154 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1645800 (The Pile)

Max Activating Token Index: 888

Text #5

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4674. Min Act: -0.0000

Data Index: 985676 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1157709 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4919. Min Act: -0.0000

Data Index: 410756 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1440651 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4455. Min Act: -0.0000

Data Index: 6579 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4734. Min Act: -0.0000

Data Index: 323959 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1163825 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1407598 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4486. Min Act: -0.0000

Data Index: 689618 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1502388 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1549988 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4657. Min Act: -0.0000

Data Index: 628145 (The Pile)

Max Activating Token Index: 756

Text #17

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1506504 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.3369. Min Act: -0.0000

Data Index: 867822 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4011. Min Act: -0.0000

Data Index: 797823 (The Pile)

Max Activating Token Index: 178