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

Dataset: The Pile

Neuron 4993 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0922. Min Range: -5.0922

Max Act: 5.0922. Min Act: -0.0000

Data Index: 14805 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 5.0922. Min Range: -5.0922

Max Act: 5.0458. Min Act: -0.0000

Data Index: 1290193 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 5.0922. Min Range: -5.0922

Max Act: 4.3733. Min Act: -0.0000

Data Index: 1884769 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 5.0922. Min Range: -5.0922

Max Act: 4.2458. Min Act: -0.0000

Data Index: 1467046 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 5.0922. Min Range: -5.0922

Max Act: 4.0580. Min Act: -0.0000

Data Index: 877224 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 5.0922. Min Range: -5.0922

Max Act: 4.2344. Min Act: -0.0000

Data Index: 1173231 (The Pile)

Max Activating Token Index: 313

Text #6

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.8546. Min Act: -0.0000

Data Index: 1515781 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 5.0922. Min Range: -5.0922

Max Act: 4.1412. Min Act: -0.0000

Data Index: 312 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.6630. Min Act: -0.0000

Data Index: 617222 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 5.0922. Min Range: -5.0922

Max Act: 4.0040. Min Act: -0.0000

Data Index: 1342982 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.7844. Min Act: -0.0000

Data Index: 370917 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.6269. Min Act: -0.0000

Data Index: 1639672 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.4607. Min Act: -0.0000

Data Index: 1749628 (The Pile)

Max Activating Token Index: 934

Text #13

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.7730. Min Act: -0.0000

Data Index: 481870 (The Pile)

Max Activating Token Index: 447

Text #14

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.4308. Min Act: -0.0000

Data Index: 1212066 (The Pile)

Max Activating Token Index: 358

Text #15

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.5841. Min Act: -0.0000

Data Index: 724433 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.7088. Min Act: -0.0000

Data Index: 1325887 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.6743. Min Act: -0.0000

Data Index: 1495985 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.7127. Min Act: -0.0000

Data Index: 616165 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 5.0922. Min Range: -5.0922

Max Act: 3.4734. Min Act: -0.0000

Data Index: 1809811 (The Pile)

Max Activating Token Index: 530