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

Dataset: The Pile

Neuron 3723 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.6574. Min Act: -0.0000

Data Index: 120201 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 3.6574. Min Range: -3.6574

Max Act: 3.6333. Min Act: -0.0000

Data Index: 1011010 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.7992. Min Act: -0.0000

Data Index: 569380 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.8726. Min Act: -0.0000

Data Index: 491809 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.7498. Min Act: -0.0000

Data Index: 1269036 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.6877. Min Act: -0.0000

Data Index: 92127 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.6380. Min Act: -0.0000

Data Index: 1077813 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.6118. Min Act: -0.0000

Data Index: 1645423 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.3509. Min Act: -0.0000

Data Index: 57189 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.5968. Min Act: -0.0000

Data Index: 495698 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.5908. Min Act: -0.0000

Data Index: 1744945 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.4526. Min Act: -0.0000

Data Index: 1545739 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.6564. Min Act: -0.0000

Data Index: 1298530 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.3969. Min Act: -0.0000

Data Index: 663053 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.3783. Min Act: -0.0000

Data Index: 866013 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.4983. Min Act: -0.0000

Data Index: 613856 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.4931. Min Act: -0.0000

Data Index: 1774498 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.4893. Min Act: -0.0000

Data Index: 393343 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.4771. Min Act: -0.0000

Data Index: 432388 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 3.6574. Min Range: -3.6574

Max Act: 2.5834. Min Act: -0.0000

Data Index: 481884 (The Pile)

Max Activating Token Index: 449