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

Dataset: The Pile

Neuron 4036 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1963. Min Act: -0.0000

Data Index: 34683 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 4.1963. Min Range: -4.1963

Max Act: 3.5248. Min Act: -0.0000

Data Index: 881407 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 4.1963. Min Range: -4.1963

Max Act: 3.7664. Min Act: -0.0000

Data Index: 1340198 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 4.1963. Min Range: -4.1963

Max Act: 3.4807. Min Act: -0.0000

Data Index: 1948994 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.9954. Min Act: 0.0000

Data Index: 820170 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.9280. Min Act: -0.0000

Data Index: 1333860 (The Pile)

Max Activating Token Index: 485

Text #6

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.5319. Min Act: -0.0000

Data Index: 1699897 (The Pile)

Max Activating Token Index: 885

Text #7

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.5284. Min Act: -0.0000

Data Index: 617006 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.3510. Min Act: -0.0000

Data Index: 530943 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.6928. Min Act: -0.0000

Data Index: 1024346 (The Pile)

Max Activating Token Index: 918

Text #10

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.3910. Min Act: -0.0000

Data Index: 181307 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.5103. Min Act: -0.0000

Data Index: 1044878 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.3246. Min Act: -0.0000

Data Index: 1952973 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.2397. Min Act: -0.0000

Data Index: 330721 (The Pile)

Max Activating Token Index: 947

Text #14

Max Range: 4.1963. Min Range: -4.1963

Max Act: 1.9511. Min Act: -0.0000

Data Index: 1186297 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.0865. Min Act: -0.0000

Data Index: 1629360 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 4.1963. Min Range: -4.1963

Max Act: 1.9668. Min Act: -0.0000

Data Index: 574696 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.0715. Min Act: -0.0000

Data Index: 672203 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 4.1963. Min Range: -4.1963

Max Act: 1.9446. Min Act: -0.0000

Data Index: 696603 (The Pile)

Max Activating Token Index: 110

Text #19

Max Range: 4.1963. Min Range: -4.1963

Max Act: 2.0602. Min Act: -0.0000

Data Index: 746505 (The Pile)

Max Activating Token Index: 607