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

Dataset: The Pile

Neuron 4770 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: 3.3599. Min Range: -3.3599

Max Act: 3.1291. Min Act: -0.0000

Data Index: 1497538 (The Pile)

Max Activating Token Index: 61

Text #1

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.3599. Min Act: -0.0000

Data Index: 1083278 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.2156. Min Act: -0.0000

Data Index: 1084619 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.1760. Min Act: -0.0000

Data Index: 595207 (The Pile)

Max Activating Token Index: 41

Text #4

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.0784. Min Act: -0.0000

Data Index: 1974031 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.0758. Min Act: -0.0000

Data Index: 1240767 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.7808. Min Act: -0.0000

Data Index: 37211 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.9112. Min Act: -0.0000

Data Index: 1783809 (The Pile)

Max Activating Token Index: 320

Text #8

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.0351. Min Act: -0.0000

Data Index: 1274059 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.8930. Min Act: -0.0000

Data Index: 1525204 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.0246. Min Act: -0.0000

Data Index: 958707 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.9874. Min Act: -0.0000

Data Index: 1748620 (The Pile)

Max Activating Token Index: 431

Text #12

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.9936. Min Act: -0.0000

Data Index: 1570420 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 3.3599. Min Range: -3.3599

Max Act: 3.0867. Min Act: -0.0000

Data Index: 1521546 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.6567. Min Act: -0.0000

Data Index: 931566 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.9619. Min Act: -0.0000

Data Index: 1868220 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.8037. Min Act: -0.0000

Data Index: 668428 (The Pile)

Max Activating Token Index: 401

Text #17

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.9418. Min Act: -0.0000

Data Index: 668880 (The Pile)

Max Activating Token Index: 718

Text #18

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.9518. Min Act: -0.0000

Data Index: 552942 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 3.3599. Min Range: -3.3599

Max Act: 2.9346. Min Act: -0.0000

Data Index: 40953 (The Pile)

Max Activating Token Index: 740