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

Dataset: The Pile

Neuron 1018 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3911. Min Range: -5.3911

Max Act: 5.3911. Min Act: -0.0000

Data Index: 1308029 (The Pile)

Max Activating Token Index: 1020

Text #1

Max Range: 5.3911. Min Range: -5.3911

Max Act: 4.6716. Min Act: -0.0000

Data Index: 1197116 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 5.3911. Min Range: -5.3911

Max Act: 4.1563. Min Act: -0.0000

Data Index: 1836719 (The Pile)

Max Activating Token Index: 955

Text #3

Max Range: 5.3911. Min Range: -5.3911

Max Act: 4.0293. Min Act: -0.0000

Data Index: 1575697 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.8287. Min Act: -0.0000

Data Index: 978197 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.9629. Min Act: -0.0000

Data Index: 1491141 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.7879. Min Act: -0.0000

Data Index: 1415133 (The Pile)

Max Activating Token Index: 544

Text #7

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.8348. Min Act: -0.0000

Data Index: 936295 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 5.3911. Min Range: -5.3911

Max Act: 4.1804. Min Act: -0.0000

Data Index: 1824923 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.9381. Min Act: -0.0000

Data Index: 1039144 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.5542. Min Act: -0.0000

Data Index: 1218474 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.9075. Min Act: -0.0000

Data Index: 539361 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.5548. Min Act: -0.0000

Data Index: 937676 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.8234. Min Act: -0.0000

Data Index: 909708 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.7562. Min Act: -0.0000

Data Index: 1249020 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.4224. Min Act: -0.0000

Data Index: 1284962 (The Pile)

Max Activating Token Index: 702

Text #16

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.2174. Min Act: -0.0000

Data Index: 578807 (The Pile)

Max Activating Token Index: 778

Text #17

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.5421. Min Act: -0.0000

Data Index: 649391 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.3861. Min Act: -0.0000

Data Index: 1012383 (The Pile)

Max Activating Token Index: 343

Text #19

Max Range: 5.3911. Min Range: -5.3911

Max Act: 3.3359. Min Act: -0.0000

Data Index: 1951872 (The Pile)

Max Activating Token Index: 385