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

Dataset: The Pile

Neuron 4547 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: 0.4766. Min Range: -0.4766

Max Act: 0.4534. Min Act: -0.0000

Data Index: 58866 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1161675 (The Pile)

Max Activating Token Index: 973

Text #2

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3844. Min Act: -0.0000

Data Index: 607421 (The Pile)

Max Activating Token Index: 402

Text #3

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4078. Min Act: -0.0000

Data Index: 19926 (The Pile)

Max Activating Token Index: 231

Text #4

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1532108 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1557691 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1324886 (The Pile)

Max Activating Token Index: 852

Text #7

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1684485 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1520278 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3945. Min Act: -0.0000

Data Index: 576397 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1377993 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1387120 (The Pile)

Max Activating Token Index: 899

Text #12

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1138834 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3710. Min Act: -0.0000

Data Index: 791624 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1823096 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1814316 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1575075 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3766. Min Act: -0.0000

Data Index: 385253 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1648679 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 0.4766. Min Range: -0.4766

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1589846 (The Pile)

Max Activating Token Index: 1001