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

Dataset: The Pile

Neuron 3658 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: 3.7884. Min Range: -3.7884

Max Act: 3.7884. Min Act: -0.0000

Data Index: 1918613 (The Pile)

Max Activating Token Index: 713

Text #1

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.4213. Min Act: -0.0000

Data Index: 481349 (The Pile)

Max Activating Token Index: 374

Text #2

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.6671. Min Act: -0.0000

Data Index: 1024445 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.3437. Min Act: -0.0000

Data Index: 937193 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.2220. Min Act: -0.0000

Data Index: 1621002 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.3016. Min Act: -0.0000

Data Index: 673160 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.1652. Min Act: -0.0000

Data Index: 118937 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.1724. Min Act: -0.0000

Data Index: 1686195 (The Pile)

Max Activating Token Index: 941

Text #8

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.9762. Min Act: -0.0000

Data Index: 68289 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.1452. Min Act: -0.0000

Data Index: 1377992 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.9622. Min Act: -0.0000

Data Index: 1580117 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.9102. Min Act: -0.0000

Data Index: 1948543 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.2370. Min Act: -0.0000

Data Index: 900036 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0794. Min Act: -0.0000

Data Index: 1095459 (The Pile)

Max Activating Token Index: 466

Text #14

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.1704. Min Act: -0.0000

Data Index: 974076 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0359. Min Act: -0.0000

Data Index: 167651 (The Pile)

Max Activating Token Index: 864

Text #16

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0656. Min Act: -0.0000

Data Index: 618057 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.2150. Min Act: -0.0000

Data Index: 1322428 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.2231. Min Act: -0.0000

Data Index: 1876073 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.9930. Min Act: -0.0000

Data Index: 637355 (The Pile)

Max Activating Token Index: 913