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

Dataset: The Pile

Neuron 3641 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: 3.9608. Min Range: -3.9608

Max Act: 3.6387. Min Act: -0.0000

Data Index: 1341630 (The Pile)

Max Activating Token Index: 32

Text #1

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.9608. Min Act: -0.0000

Data Index: 1139882 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.7265. Min Act: -0.0000

Data Index: 769131 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.5688. Min Act: -0.0000

Data Index: 769594 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 3.9608. Min Range: -3.9608

Max Act: 2.9399. Min Act: -0.0000

Data Index: 86022 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.3355. Min Act: -0.0000

Data Index: 1895904 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 3.9608. Min Range: -3.9608

Max Act: 2.9617. Min Act: -0.0000

Data Index: 1911066 (The Pile)

Max Activating Token Index: 966

Text #7

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.1074. Min Act: -0.0000

Data Index: 1788364 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.2823. Min Act: -0.0000

Data Index: 392272 (The Pile)

Max Activating Token Index: 418

Text #9

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.1779. Min Act: -0.0000

Data Index: 1400535 (The Pile)

Max Activating Token Index: 317

Text #10

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.0012. Min Act: -0.0000

Data Index: 337635 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 3.9608. Min Range: -3.9608

Max Act: 2.9276. Min Act: -0.0000

Data Index: 814739 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.0637. Min Act: -0.0000

Data Index: 376559 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 3.9608. Min Range: -3.9608

Max Act: 2.9821. Min Act: -0.0000

Data Index: 825823 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 3.9608. Min Range: -3.9608

Max Act: 2.7978. Min Act: -0.0000

Data Index: 235099 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 3.9608. Min Range: -3.9608

Max Act: 2.8902. Min Act: -0.0000

Data Index: 1533666 (The Pile)

Max Activating Token Index: 976

Text #16

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.1205. Min Act: -0.0000

Data Index: 460051 (The Pile)

Max Activating Token Index: 595

Text #17

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.0099. Min Act: -0.0000

Data Index: 174603 (The Pile)

Max Activating Token Index: 740

Text #18

Max Range: 3.9608. Min Range: -3.9608

Max Act: 3.1335. Min Act: -0.0000

Data Index: 1260452 (The Pile)

Max Activating Token Index: 873

Text #19

Max Range: 3.9608. Min Range: -3.9608

Max Act: 2.8680. Min Act: -0.0000

Data Index: 1601020 (The Pile)

Max Activating Token Index: 124